Fangzhou Hong

Zhongang Cai, Daxuan Ren, Ailing Zeng et al.

4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications. With the advances of new sensors and algorithms, there is an increasing demand for more versatile datasets. In this work, we contribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 human subjects, 400k sequences and 60M frames. HuMMan has several appealing properties: 1) multi-modal data and annotations including color images, point clouds, keypoints, SMPL parameters, and textured meshes; 2) popular mobile device is included in the sensor suite; 3) a set of 500 actions, designed to cover fundamental movements; 4) multiple tasks such as action recognition, pose estimation, parametric human recovery, and textured mesh reconstruction are supported and evaluated. Extensive experiments on HuMMan voice the need for further study on challenges such as fine-grained action recognition, dynamic human mesh reconstruction, point cloud-based parametric human recovery, and cross-device domain gaps.

Mingyuan Zhang, Zhongang Cai, Liang Pan et al.

Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent motion generation methods can directly generate human motions conditioned on natural languages. However, it remains challenging to achieve diverse and fine-grained motion generation with various text inputs. To address this problem, we propose MotionDiffuse, the first diffusion model-based text-driven motion generation framework, which demonstrates several desired properties over existing methods. 1) Probabilistic Mapping. Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected. 2) Realistic Synthesis. MotionDiffuse excels at modeling complicated data distribution and generating vivid motion sequences. 3) Multi-Level Manipulation. MotionDiffuse responds to fine-grained instructions on body parts, and arbitrary-length motion synthesis with time-varied text prompts. Our experiments show MotionDiffuse outperforms existing SoTA methods by convincing margins on text-driven motion generation and action-conditioned motion generation. A qualitative analysis further demonstrates MotionDiffuse's controllability for comprehensive motion generation. Homepage: https://mingyuan-zhang.github.io/projects/MotionDiffuse.html

Junzhe Zhang, Yushi Lan, Shuai Yang et al.

In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture. Although fine-tuning a pre-trained 3D GAN on the artistic domain can produce reasonable performance, this strategy has limitations in the 3D domain. In particular, fine-tuning can deteriorate the original GAN latent space, which affects subsequent semantic editing, and requires independent optimization and storage for each new style, limiting flexibility and efficient deployment. To overcome these challenges, we propose DeformToon3D, an effective toonification framework tailored for hierarchical 3D GAN. Our approach decomposes 3D toonification into subproblems of geometry and texture stylization to better preserve the original latent space. Specifically, we devise a novel StyleField that predicts conditional 3D deformation to align a real-space NeRF to the style space for geometry stylization. Thanks to the StyleField formulation, which already handles geometry stylization well, texture stylization can be achieved conveniently via adaptive style mixing that injects information of the artistic domain into the decoder of the pre-trained 3D GAN. Due to the unique design, our method enables flexible style degree control and shape-texture-specific style swap. Furthermore, we achieve efficient training without any real-world 2D-3D training pairs but proxy samples synthesized from off-the-shelf 2D toonification models.

Mingyuan Zhang, Xinying Guo, Liang Pan et al.

3D human motion generation is crucial for creative industry. Recent advances rely on generative models with domain knowledge for text-driven motion generation, leading to substantial progress in capturing common motions. However, the performance on more diverse motions remains unsatisfactory. In this work, we propose ReMoDiffuse, a diffusion-model-based motion generation framework that integrates a retrieval mechanism to refine the denoising process. ReMoDiffuse enhances the generalizability and diversity of text-driven motion generation with three key designs: 1) Hybrid Retrieval finds appropriate references from the database in terms of both semantic and kinematic similarities. 2) Semantic-Modulated Transformer selectively absorbs retrieval knowledge, adapting to the difference between retrieved samples and the target motion sequence. 3) Condition Mixture better utilizes the retrieval database during inference, overcoming the scale sensitivity in classifier-free guidance. Extensive experiments demonstrate that ReMoDiffuse outperforms state-of-the-art methods by balancing both text-motion consistency and motion quality, especially for more diverse motion generation.

Zhongang Cai, Liang Pan, Chen Wei et al.

Human pose and shape estimation (HPS) has attracted increasing attention in recent years. While most existing studies focus on HPS from 2D images or videos with inherent depth ambiguity, there are surging need to investigate HPS from 3D point clouds as depth sensors have been frequently employed in commercial devices. However, real-world sensory 3D points are usually noisy and incomplete, and also human bodies could have different poses of high diversity. To tackle these challenges, we propose a principled framework, PointHPS, for accurate 3D HPS from point clouds captured in real-world settings, which iteratively refines point features through a cascaded architecture. Specifically, each stage of PointHPS performs a series of downsampling and upsampling operations to extract and collate both local and global cues, which are further enhanced by two novel modules: 1) Cross-stage Feature Fusion (CFF) for multi-scale feature propagation that allows information to flow effectively through the stages, and 2) Intermediate Feature Enhancement (IFE) for body-aware feature aggregation that improves feature quality after each stage. To facilitate a comprehensive study under various scenarios, we conduct our experiments on two large-scale benchmarks, comprising i) a dataset that features diverse subjects and actions captured by real commercial sensors in a laboratory environment, and ii) controlled synthetic data generated with realistic considerations such as clothed humans in crowded outdoor scenes. Extensive experiments demonstrate that PointHPS, with its powerful point feature extraction and processing scheme, outperforms State-of-the-Art methods by significant margins across the board. Homepage: https://caizhongang.github.io/projects/PointHPS/.

Fangzhou Hong, Zhaoxi Chen, Yushi Lan et al.

Inverse graphics aims to recover 3D models from 2D observations. Utilizing differentiable rendering, recent 3D-aware generative models have shown impressive results of rigid object generation using 2D images. However, it remains challenging to generate articulated objects, like human bodies, due to their complexity and diversity in poses and appearances. In this work, we propose, EVA3D, an unconditional 3D human generative model learned from 2D image collections only. EVA3D can sample 3D humans with detailed geometry and render high-quality images (up to 512x256) without bells and whistles (e.g. super resolution). At the core of EVA3D is a compositional human NeRF representation, which divides the human body into local parts. Each part is represented by an individual volume. This compositional representation enables 1) inherent human priors, 2) adaptive allocation of network parameters, 3) efficient training and rendering. Moreover, to accommodate for the characteristics of sparse 2D human image collections (e.g. imbalanced pose distribution), we propose a pose-guided sampling strategy for better GAN learning. Extensive experiments validate that EVA3D achieves state-of-the-art 3D human generation performance regarding both geometry and texture quality. Notably, EVA3D demonstrates great potential and scalability to "inverse-graphics" diverse human bodies with a clean framework.

Shoukang Hu, Fangzhou Hong, Liang Pan et al.

Existing Human NeRF methods for reconstructing 3D humans typically rely on multiple 2D images from multi-view cameras or monocular videos captured from fixed camera views. However, in real-world scenarios, human images are often captured from random camera angles, presenting challenges for high-quality 3D human reconstruction. In this paper, we propose SHERF, the first generalizable Human NeRF model for recovering animatable 3D humans from a single input image. SHERF extracts and encodes 3D human representations in canonical space, enabling rendering and animation from free views and poses. To achieve high-fidelity novel view and pose synthesis, the encoded 3D human representations should capture both global appearance and local fine-grained textures. To this end, we propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding. Global features enhance the information extracted from the single input image and complement the information missing from the partial 2D observation. Point-level features provide strong clues of 3D human structure, while pixel-aligned features preserve more fine-grained details. To effectively integrate the 3D-aware hierarchical feature bank, we design a feature fusion transformer. Extensive experiments on THuman, RenderPeople, ZJU_MoCap, and HuMMan datasets demonstrate that SHERF achieves state-of-the-art performance, with better generalizability for novel view and pose synthesis.

Fangzhou Hong, Mingyuan Zhang, Liang Pan et al.

3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability.

Ziang Cao, Fangzhou Hong, Tong Wu et al.

Creating diverse and high-quality 3D assets with an automatic generative model is highly desirable. Despite extensive efforts on 3D generation, most existing works focus on the generation of a single category or a few categories. In this paper, we introduce a diffusion-based feed-forward framework for synthesizing massive categories of real-world 3D objects with a single generative model. Notably, there are three major challenges for this large-vocabulary 3D generation: a) the need for expressive yet efficient 3D representation; b) large diversity in geometry and texture across categories; c) complexity in the appearances of real-world objects. To this end, we propose a novel triplane-based 3D-aware Diffusion model with TransFormer, DiffTF, for handling challenges via three aspects. 1) Considering efficiency and robustness, we adopt a revised triplane representation and improve the fitting speed and accuracy. 2) To handle the drastic variations in geometry and texture, we regard the features of all 3D objects as a combination of generalized 3D knowledge and specialized 3D features. To extract generalized 3D knowledge from diverse categories, we propose a novel 3D-aware transformer with shared cross-plane attention. It learns the cross-plane relations across different planes and aggregates the generalized 3D knowledge with specialized 3D features. 3) In addition, we devise the 3D-aware encoder/decoder to enhance the generalized 3D knowledge in the encoded triplanes for handling categories with complex appearances. Extensive experiments on ShapeNet and OmniObject3D (over 200 diverse real-world categories) convincingly demonstrate that a single DiffTF model achieves state-of-the-art large-vocabulary 3D object generation performance with large diversity, rich semantics, and high quality.

Zhaoxi Chen, Jiaxiang Tang, Yuhao Dong et al.

The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative models, existing methods still face challenges with optimization speed, geometric fidelity, and the lack of assets for physically based rendering (PBR). In this paper, we introduce 3DTopia-XL, a scalable native 3D generative model designed to overcome these limitations. 3DTopia-XL leverages a novel primitive-based 3D representation, PrimX, which encodes detailed shape, albedo, and material field into a compact tensorial format, facilitating the modeling of high-resolution geometry with PBR assets. On top of the novel representation, we propose a generative framework based on Diffusion Transformer (DiT), which comprises 1) Primitive Patch Compression, 2) and Latent Primitive Diffusion. 3DTopia-XL learns to generate high-quality 3D assets from textual or visual inputs. We conduct extensive qualitative and quantitative experiments to demonstrate that 3DTopia-XL significantly outperforms existing methods in generating high-quality 3D assets with fine-grained textures and materials, efficiently bridging the quality gap between generative models and real-world applications.

Fangzhou Hong, Liang Pan, Zhongang Cai et al.

Human-centric perception plays a vital role in vision and graphics. But their data annotations are prohibitively expensive. Therefore, it is desirable to have a versatile pre-train model that serves as a foundation for data-efficient downstream tasks transfer. To this end, we propose the Human-Centric Multi-Modal Contrastive Learning framework HCMoCo that leverages the multi-modal nature of human data (e.g. RGB, depth, 2D keypoints) for effective representation learning. The objective comes with two main challenges: dense pre-train for multi-modality data, efficient usage of sparse human priors. To tackle the challenges, we design the novel Dense Intra-sample Contrastive Learning and Sparse Structure-aware Contrastive Learning targets by hierarchically learning a modal-invariant latent space featured with continuous and ordinal feature distribution and structure-aware semantic consistency. HCMoCo provides pre-train for different modalities by combining heterogeneous datasets, which allows efficient usage of existing task-specific human data. Extensive experiments on four downstream tasks of different modalities demonstrate the effectiveness of HCMoCo, especially under data-efficient settings (7.16% and 12% improvement on DensePose Estimation and Human Parsing). Moreover, we demonstrate the versatility of HCMoCo by exploring cross-modality supervision and missing-modality inference, validating its strong ability in cross-modal association and reasoning.

Shoukang Hu, Fangzhou Hong, Tao Hu et al.

3D human generation from 2D images has achieved remarkable progress through the synergistic utilization of neural rendering and generative models. Existing 3D human generative models mainly generate a clothed 3D human as an undetectable 3D model in a single pass, while rarely considering the layer-wise nature of a clothed human body, which often consists of the human body and various clothes such as underwear, outerwear, trousers, shoes, etc. In this work, we propose HumanLiff, the first layer-wise 3D human generative model with a unified diffusion process. Specifically, HumanLiff firstly generates minimal-clothed humans, represented by tri-plane features, in a canonical space, and then progressively generates clothes in a layer-wise manner. In this way, the 3D human generation is thus formulated as a sequence of diffusion-based 3D conditional generation. To reconstruct more fine-grained 3D humans with tri-plane representation, we propose a tri-plane shift operation that splits each tri-plane into three sub-planes and shifts these sub-planes to enable feature grid subdivision. To further enhance the controllability of 3D generation with 3D layered conditions, HumanLiff hierarchically fuses tri-plane features and 3D layered conditions to facilitate the 3D diffusion model learning. Extensive experiments on two layer-wise 3D human datasets, SynBody (synthetic) and TightCap (real-world), validate that HumanLiff significantly outperforms state-of-the-art methods in layer-wise 3D human generation. Our code will be available at https://skhu101.github.io/HumanLiff.

Fangzhou Hong, Hui Zhou, Xinge Zhu et al.

With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the objects (e.g. cars and pedestrians) or scenes (e.g. trees and buildings) from the LiDAR sensor. In this work, we address the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner. As one of the first endeavors towards this new challenging task, we propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. In particular, DS-Net has three appealing properties: 1) Strong backbone design. DS-Net adopts the cylinder convolution that is specifically designed for LiDAR point clouds. 2) Dynamic Shifting for complex point distributions. We observe that commonly-used clustering algorithms are incapable of handling complex autonomous driving scenes with non-uniform point cloud distributions and varying instance sizes. Thus, we present an efficient learnable clustering module, dynamic shifting, which adapts kernel functions on the fly for different instances. 3) Extension to 4D prediction. Furthermore, we extend DS-Net to 4D panoptic LiDAR segmentation by the temporally unified instance clustering on aligned LiDAR frames. To comprehensively evaluate the performance of LiDAR-based panoptic segmentation, we construct and curate benchmarks from two large-scale autonomous driving LiDAR datasets, SemanticKITTI and nuScenes. Extensive experiments demonstrate that our proposed DS-Net achieves superior accuracies over current state-of-the-art methods in both tasks. Notably, in the single frame version of the task, we outperform the SOTA method by 1.8% in terms of the PQ metric. In the 4D version of the task, we surpass 2nd place by 5.4% in terms of the LSTQ metric.

Haosong Peng, Hao Li, Jiaqi Chen et al.

While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.

Haozhe Xie, Beichen Wen, Jiarui Zheng et al.

Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in dynamic scenarios requiring rapid perception, temporal anticipation, and continuous control. We present DynamicVLA, a framework for dynamic object manipulation that integrates temporal reasoning and closed-loop adaptation through three key designs: 1) a compact 0.4B VLA using a convolutional vision encoder for spatially efficient, structurally faithful encoding, enabling fast multimodal inference; 2) Continuous Inference, enabling overlapping reasoning and execution for lower latency and timely adaptation to object motion; and 3) Latent-aware Action Streaming, which bridges the perception-execution gap by enforcing temporally aligned action execution. To fill the missing foundation of dynamic manipulation data, we introduce the Dynamic Object Manipulation (DOM) benchmark, built from scratch with an auto data collection pipeline that efficiently gathers 200K synthetic episodes across 2.8K scenes and 206 objects, and enables fast collection of 2K real-world episodes without teleoperation. Extensive evaluations demonstrate remarkable improvements in response speed, perception, and generalization, positioning DynamicVLA as a unified framework for general dynamic object manipulation across embodiments.

Vladimir Guzov, Yifeng Jiang, Fangzhou Hong et al.

This paper investigates the generation of realistic full-body human motion using a single head-mounted device with an outward-facing color camera and the ability to perform visual SLAM. To address the ambiguity of this setup, we present HMD^2, a novel system that balances motion reconstruction and generation. From a reconstruction standpoint, it aims to maximally utilize the camera streams to produce both analytical and learned features, including head motion, SLAM point cloud, and image embeddings. On the generative front, HMD^2 employs a multi-modal conditional motion diffusion model with a Transformer backbone to maintain temporal coherence of generated motions, and utilizes autoregressive inpainting to facilitate online motion inference with minimal latency (0.17 seconds). We show that our system provides an effective and robust solution that scales to a diverse dataset of over 200 hours of motion in complex indoor and outdoor environments.

Fangzhou Hong, Jiaxiang Tang, Ziang Cao et al.

We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping. The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality texture generation. To facilitate the training of the proposed system, we clean and caption the largest open-source 3D dataset, Objaverse, by combining the power of vision language models and large language models. Experiment results are reported qualitatively and quantitatively to show the performance of the proposed system. Our codes and models are available at https://github.com/3DTopia/3DTopia

Fangzhou Hong, Vladimir Guzov, Hyo Jin Kim et al.

As the prevalence of wearable devices, learning egocentric motions becomes essential to develop contextual AI. In this work, we present EgoLM, a versatile framework that tracks and understands egocentric motions from multi-modal inputs, e.g., egocentric videos and motion sensors. EgoLM exploits rich contexts for the disambiguation of egomotion tracking and understanding, which are ill-posed under single modality conditions. To facilitate the versatile and multi-modal framework, our key insight is to model the joint distribution of egocentric motions and natural languages using large language models (LLM). Multi-modal sensor inputs are encoded and projected to the joint latent space of language models, and used to prompt motion generation or text generation for egomotion tracking or understanding, respectively. Extensive experiments on large-scale multi-modal human motion dataset validate the effectiveness of EgoLM as a generalist model for universal egocentric learning.

Ziang Cao, Yinghao Liu, Haitian Li et al.

Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.

Haitian Li, Haozhe Xie, Junxiang Xu et al.

Reconstructing articulated 3D objects from a single image requires jointly inferring object geometry, part structure, and motion parameters from limited visual evidence. A key difficulty lies in the entanglement between motion cues and object structure, which makes direct articulation regression unstable. Existing methods address this challenge through multi-view supervision, retrieval-based assembly, or auxiliary video generation, often sacrificing scalability or efficiency. We present MonoArt, a unified framework grounded in progressive structural reasoning. Rather than predicting articulation directly from image features, MonoArt progressively transforms visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture. This structured reasoning process enables stable and interpretable articulation inference without external motion templates or multi-stage pipelines. Extensive experiments on PartNet-Mobility demonstrate that OM achieves state-of-the-art performance in both reconstruction accuracy and inference speed. The framework further generalizes to robotic manipulation and articulated scene reconstruction.

Yukang Cao, Jiahao Lu, Zhisheng Huang et al.

Reconstructing 4D spatial intelligence from visual observations has long been a central yet challenging task in computer vision, with broad real-world applications. These range from entertainment domains like movies, where the focus is often on reconstructing fundamental visual elements, to embodied AI, which emphasizes interaction modeling and physical realism. Fueled by rapid advances in 3D representations and deep learning architectures, the field has evolved quickly, outpacing the scope of previous surveys. Additionally, existing surveys rarely offer a comprehensive analysis of the hierarchical structure of 4D scene reconstruction. To address this gap, we present a new perspective that organizes existing methods into five progressive levels of 4D spatial intelligence: (1) Level 1 -- reconstruction of low-level 3D attributes (e.g., depth, pose, and point maps); (2) Level 2 -- reconstruction of 3D scene components (e.g., objects, humans, structures); (3) Level 3 -- reconstruction of 4D dynamic scenes; (4) Level 4 -- modeling of interactions among scene components; and (5) Level 5 -- incorporation of physical laws and constraints. We conclude the survey by discussing the key challenges at each level and highlighting promising directions for advancing toward even richer levels of 4D spatial intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/yukangcao/Awesome-4D-Spatial-Intelligence.

Beichen Wen, Haozhe Xie, Zhaoxi Chen et al.

3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on procedural rules offered scalability but limited diversity. Recent advances in deep generative models (e.g., GANs, diffusion models) and 3D representations (e.g., NeRF, 3D Gaussians) have enabled the learning of real-world scene distributions, improving fidelity, diversity, and view consistency. Recent advances like diffusion models bridge 3D scene synthesis and photorealism by reframing generation as image or video synthesis problems. This survey provides a systematic overview of state-of-the-art approaches, organizing them into four paradigms: procedural generation, neural 3D-based generation, image-based generation, and video-based generation. We analyze their technical foundations, trade-offs, and representative results, and review commonly used datasets, evaluation protocols, and downstream applications. We conclude by discussing key challenges in generation capacity, 3D representation, data and annotations, and evaluation, and outline promising directions including higher fidelity, physics-aware and interactive generation, and unified perception-generation models. This review organizes recent advances in 3D scene generation and highlights promising directions at the intersection of generative AI, 3D vision, and embodied intelligence. To track ongoing developments, we maintain an up-to-date project page: https://github.com/hzxie/Awesome-3D-Scene-Generation.

Yukang Cao, Haozhe Xie, Fangzhou Hong et al.

We present HSImul3R, a unified framework for simulation-ready 3D reconstruction of human-scene interactions (HSI) from casual captures, including sparse-view images and monocular videos. Existing methods suffer from a perception-simulation gap: visually plausible reconstructions often violate physical constraints, leading to instability in physics engines and failure in embodied AI applications. To bridge this gap, we introduce a physically-grounded bi-directional optimization pipeline that treats the physics simulator as an active supervisor to jointly refine human dynamics and scene geometry. In the forward direction, we employ Scene-targeted Reinforcement Learning to optimize human motion under dual supervision of motion fidelity and contact stability. In the reverse direction, we propose Direct Simulation Reward Optimization, which leverages simulation feedback on gravitational stability and interaction success to refine scene geometry. We further present HSIBench, a new benchmark with diverse objects and interaction scenarios. Extensive experiments demonstrate that HSImul3R produces the first stable, simulation-ready HSI reconstructions and can be directly deployed to real-world humanoid robots.

Lingni Ma, Yuting Ye, Fangzhou Hong et al.

We introduce Nymeria - a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) full-body ground-truth motion; b) multiple multimodal egocentric data from Project Aria devices with videos, eye tracking, IMUs and etc; and c) a third-person perspective by an additional observer. All devices are precisely synchronized and localized in on metric 3D world. We derive hierarchical protocol to add in-context language descriptions of human motion, from fine-grain motion narration, to simplified atomic action and high-level activity summarization. To the best of our knowledge, Nymeria dataset is the world's largest collection of human motion in the wild; first of its kind to provide synchronized and localized multi-device multimodal egocentric data; and the world's largest motion-language dataset. It provides 300 hours of daily activities from 264 participants across 50 locations, total travelling distance over 399Km. The language descriptions contain 301.5K sentences in 8.64M words from a vocabulary size of 6545. To demonstrate the potential of the dataset, we evaluate several SOTA algorithms for egocentric body tracking, motion synthesis, and action recognition. Data and code are open-sourced for research (c.f. https://www.projectaria.com/datasets/nymeria).

Fangzhou Hong, Liang Pan, Zhongang Cai et al.

Learning to reconstruct 3D garments is important for dressing 3D human bodies of different shapes in different poses. Previous works typically rely on 2D images as input, which however suffer from the scale and pose ambiguities. To circumvent the problems caused by 2D images, we propose a principled framework, Garment4D, that uses 3D point cloud sequences of dressed humans for garment reconstruction. Garment4D has three dedicated steps: sequential garments registration, canonical garment estimation, and posed garment reconstruction. The main challenges are two-fold: 1) effective 3D feature learning for fine details, and 2) capture of garment dynamics caused by the interaction between garments and the human body, especially for loose garments like skirts. To unravel these problems, we introduce a novel Proposal-Guided Hierarchical Feature Network and Iterative Graph Convolution Network, which integrate both high-level semantic features and low-level geometric features for fine details reconstruction. Furthermore, we propose a Temporal Transformer for smooth garment motions capture. Unlike non-parametric methods, the reconstructed garment meshes by our method are separable from the human body and have strong interpretability, which is desirable for downstream tasks. As the first attempt at this task, high-quality reconstruction results are qualitatively and quantitatively illustrated through extensive experiments. Codes are available at https://github.com/hongfz16/Garment4D.

Yushi Lan, Fangzhou Hong, Shuai Yang et al.

The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled. This paper introduces a novel framework called LN3Diff to address this gap and enable fast, high-quality, and generic conditional 3D generation. Our approach harnesses a 3D-aware architecture and variational autoencoder (VAE) to encode the input image into a structured, compact, and 3D latent space. The latent is decoded by a transformer-based decoder into a high-capacity 3D neural field. Through training a diffusion model on this 3D-aware latent space, our method achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation across various datasets. Moreover, it surpasses existing 3D diffusion methods in terms of inference speed, requiring no per-instance optimization. Our proposed LN3Diff presents a significant advancement in 3D generative modeling and holds promise for various applications in 3D vision and graphics tasks.

Mingyuan Zhang, Daisheng Jin, Chenyang Gu et al.

Human motion generation, a cornerstone technique in animation and video production, has widespread applications in various tasks like text-to-motion and music-to-dance. Previous works focus on developing specialist models tailored for each task without scalability. In this work, we present Large Motion Model (LMM), a motion-centric, multi-modal framework that unifies mainstream motion generation tasks into a generalist model. A unified motion model is appealing since it can leverage a wide range of motion data to achieve broad generalization beyond a single task. However, it is also challenging due to the heterogeneous nature of substantially different motion data and tasks. LMM tackles these challenges from three principled aspects: 1) Data: We consolidate datasets with different modalities, formats and tasks into a comprehensive yet unified motion generation dataset, MotionVerse, comprising 10 tasks, 16 datasets, a total of 320k sequences, and 100 million frames. 2) Architecture: We design an articulated attention mechanism ArtAttention that incorporates body part-aware modeling into Diffusion Transformer backbone. 3) Pre-Training: We propose a novel pre-training strategy for LMM, which employs variable frame rates and masking forms, to better exploit knowledge from diverse training data. Extensive experiments demonstrate that our generalist LMM achieves competitive performance across various standard motion generation tasks over state-of-the-art specialist models. Notably, LMM exhibits strong generalization capabilities and emerging properties across many unseen tasks. Additionally, our ablation studies reveal valuable insights about training and scaling up large motion models for future research.

Zhaoxi Chen, Fangzhou Hong, Haiyi Mei et al.

We present PrimDiffusion, the first diffusion-based framework for 3D human generation. Devising diffusion models for 3D human generation is difficult due to the intensive computational cost of 3D representations and the articulated topology of 3D humans. To tackle these challenges, our key insight is operating the denoising diffusion process directly on a set of volumetric primitives, which models the human body as a number of small volumes with radiance and kinematic information. This volumetric primitives representation marries the capacity of volumetric representations with the efficiency of primitive-based rendering. Our PrimDiffusion framework has three appealing properties: 1) compact and expressive parameter space for the diffusion model, 2) flexible 3D representation that incorporates human prior, and 3) decoder-free rendering for efficient novel-view and novel-pose synthesis. Extensive experiments validate that PrimDiffusion outperforms state-of-the-art methods in 3D human generation. Notably, compared to GAN-based methods, our PrimDiffusion supports real-time rendering of high-quality 3D humans at a resolution of $512\times512$ once the denoising process is done. We also demonstrate the flexibility of our framework on training-free conditional generation such as texture transfer and 3D inpainting.

Jingkang Yang, Shuai Liu, Hongming Guo et al.

We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data collection study where six participants lived together for one week, continuously recording their daily activities - including discussions, shopping, cooking, socializing, and entertainment - using AI glasses for multimodal egocentric video capture, along with synchronized third-person-view video references. This effort resulted in the EgoLife Dataset, a comprehensive 300-hour egocentric, interpersonal, multiview, and multimodal daily life dataset with intensive annotation. Leveraging this dataset, we introduce EgoLifeQA, a suite of long-context, life-oriented question-answering tasks designed to provide meaningful assistance in daily life by addressing practical questions such as recalling past relevant events, monitoring health habits, and offering personalized recommendations. To address the key technical challenges of (1) developing robust visual-audio models for egocentric data, (2) enabling identity recognition, and (3) facilitating long-context question answering over extensive temporal information, we introduce EgoButler, an integrated system comprising EgoGPT and EgoRAG. EgoGPT is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. EgoRAG is a retrieval-based component that supports answering ultra-long-context questions. Our experimental studies verify their working mechanisms and reveal critical factors and bottlenecks, guiding future improvements. By releasing our datasets, models, and benchmarks, we aim to stimulate further research in egocentric AI assistants.

Jingkang Yang, Jun Cen, Wenxuan Peng et al.

We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph (PSG-4D), a new representation that bridges the raw visual data perceived in a dynamic 4D world and high-level visual understanding. Specifically, PSG-4D abstracts rich 4D sensory data into nodes, which represent entities with precise location and status information, and edges, which capture the temporal relations. To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs. To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component. Extensive experiments on the new dataset show that our method can serve as a strong baseline for future research on PSG-4D. In the end, we provide a real-world application example to demonstrate how we can achieve dynamic scene understanding by integrating a large language model into our PSG-4D system.

Tao Hu, Fangzhou Hong, Ziwei Liu

Recent 3D human generative models have achieved remarkable progress by learning 3D-aware GANs from 2D images. However, existing 3D human generative methods model humans in a compact 1D latent space, ignoring the articulated structure and semantics of human body topology. In this paper, we explore more expressive and higher-dimensional latent space for 3D human modeling and propose StructLDM, a diffusion-based unconditional 3D human generative model, which is learned from 2D images. StructLDM solves the challenges imposed due to the high-dimensional growth of latent space with three key designs: 1) A semantic structured latent space defined on the dense surface manifold of a statistical human body template. 2) A structured 3D-aware auto-decoder that factorizes the global latent space into several semantic body parts parameterized by a set of conditional structured local NeRFs anchored to the body template, which embeds the properties learned from the 2D training data and can be decoded to render view-consistent humans under different poses and clothing styles. 3) A structured latent diffusion model for generative human appearance sampling. Extensive experiments validate StructLDM's state-of-the-art generation performance and illustrate the expressiveness of the structured latent space over the well-adopted 1D latent space. Notably, StructLDM enables different levels of controllable 3D human generation and editing, including pose/view/shape control, and high-level tasks including compositional generations, part-aware clothing editing, 3D virtual try-on, etc. Our project page is at: https://taohuumd.github.io/projects/StructLDM/.

Ziang Cao, Fangzhou Hong, Tong Wu et al.

Generating diverse and high-quality 3D assets automatically poses a fundamental yet challenging task in 3D computer vision. Despite extensive efforts in 3D generation, existing optimization-based approaches struggle to produce large-scale 3D assets efficiently. Meanwhile, feed-forward methods often focus on generating only a single category or a few categories, limiting their generalizability. Therefore, we introduce a diffusion-based feed-forward framework to address these challenges with a single model. To handle the large diversity and complexity in geometry and texture across categories efficiently, we 1) adopt improved triplane to guarantee efficiency; 2) introduce the 3D-aware transformer to aggregate the generalized 3D knowledge with specialized 3D features; and 3) devise the 3D-aware encoder/decoder to enhance the generalized 3D knowledge. Building upon our 3D-aware Diffusion model with TransFormer, DiffTF, we propose a stronger version for 3D generation, i.e., DiffTF++. It boils down to two parts: multi-view reconstruction loss and triplane refinement. Specifically, we utilize multi-view reconstruction loss to fine-tune the diffusion model and triplane decoder, thereby avoiding the negative influence caused by reconstruction errors and improving texture synthesis. By eliminating the mismatch between the two stages, the generative performance is enhanced, especially in texture. Additionally, a 3D-aware refinement process is introduced to filter out artifacts and refine triplanes, resulting in the generation of more intricate and reasonable details. Extensive experiments on ShapeNet and OmniObject3D convincingly demonstrate the effectiveness of our proposed modules and the state-of-the-art 3D object generation performance with large diversity, rich semantics, and high quality.

Tao Hu, Fangzhou Hong, Ziwei Liu

Dynamic human rendering from video sequences has achieved remarkable progress by formulating the rendering as a mapping from static poses to human images. However, existing methods focus on the human appearance reconstruction of every single frame while the temporal motion relations are not fully explored. In this paper, we propose a new 4D motion modeling paradigm, SurMo, that jointly models the temporal dynamics and human appearances in a unified framework with three key designs: 1) Surface-based motion encoding that models 4D human motions with an efficient compact surface-based triplane. It encodes both spatial and temporal motion relations on the dense surface manifold of a statistical body template, which inherits body topology priors for generalizable novel view synthesis with sparse training observations. 2) Physical motion decoding that is designed to encourage physical motion learning by decoding the motion triplane features at timestep t to predict both spatial derivatives and temporal derivatives at the next timestep t+1 in the training stage. 3) 4D appearance decoding that renders the motion triplanes into images by an efficient volumetric surface-conditioned renderer that focuses on the rendering of body surfaces with motion learning conditioning. Extensive experiments validate the state-of-the-art performance of our new paradigm and illustrate the expressiveness of surface-based motion triplanes for rendering high-fidelity view-consistent humans with fast motions and even motion-dependent shadows. Our project page is at: https://taohuumd.github.io/projects/SurMo/

Haozhe Xie, Zhaoxi Chen, Fangzhou Hong et al.

3D scene generation has garnered growing attention in recent years and has made significant progress. Generating 4D cities is more challenging than 3D scenes due to the presence of structurally complex, visually diverse objects like buildings and vehicles, and heightened human sensitivity to distortions in urban environments. To tackle these issues, we propose CityDreamer4D, a compositional generative model specifically tailored for generating unbounded 4D cities. Our main insights are 1) 4D city generation should separate dynamic objects (e.g., vehicles) from static scenes (e.g., buildings and roads), and 2) all objects in the 4D scene should be composed of different types of neural fields for buildings, vehicles, and background stuff. Specifically, we propose Traffic Scenario Generator and Unbounded Layout Generator to produce dynamic traffic scenarios and static city layouts using a highly compact BEV representation. Objects in 4D cities are generated by combining stuff-oriented and instance-oriented neural fields for background stuff, buildings, and vehicles. To suit the distinct characteristics of background stuff and instances, the neural fields employ customized generative hash grids and periodic positional embeddings as scene parameterizations. Furthermore, we offer a comprehensive suite of datasets for city generation, including OSM, GoogleEarth, and CityTopia. The OSM dataset provides a variety of real-world city layouts, while the Google Earth and CityTopia datasets deliver large-scale, high-quality city imagery complete with 3D instance annotations. Leveraging its compositional design, CityDreamer4D supports a range of downstream applications, such as instance editing, city stylization, and urban simulation, while delivering state-of-the-art performance in generating realistic 4D cities.

Yushi Lan, Yihang Luo, Fangzhou Hong et al.

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global optimization or rely on simplistic memory mechanisms that scale poorly with sequence length. In contrast, STream3R introduces an streaming framework that processes image sequences efficiently using causal attention, inspired by advances in modern language modeling. By learning geometric priors from large-scale 3D datasets, STream3R generalizes well to diverse and challenging scenarios, including dynamic scenes where traditional methods often fail. Extensive experiments show that our method consistently outperforms prior work across both static and dynamic scene benchmarks. Moreover, STream3R is inherently compatible with LLM-style training infrastructure, enabling efficient large-scale pretraining and fine-tuning for various downstream 3D tasks. Our results underscore the potential of causal Transformer models for online 3D perception, paving the way for real-time 3D understanding in streaming environments. More details can be found in our project page: https://nirvanalan.github.io/projects/stream3r.

Zhaoxi Chen, Tianqi Liu, Long Zhuo et al.

We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) we propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for 4D modeling. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX outperforms existing 4D generation methods in efficiency and generalizability, offering a scalable solution for image-to-4D modeling and laying the foundation for generative 4D world models that simulate dynamic scene evolution.

Yuhan Wang, Fangzhou Hong, Shuai Yang et al.

Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver promising results, largely due to the challenges of scaling multiview attention to higher resolutions. In this paper, we explore human multiview diffusion models at the megapixel level and introduce a solution called mesh attention to enable training at 1024x1024 resolution. Using a clothed human mesh as a central coarse geometric representation, the proposed mesh attention leverages rasterization and projection to establish direct cross-view coordinate correspondences. This approach significantly reduces the complexity of multiview attention while maintaining cross-view consistency. Building on this foundation, we devise a mesh attention block and combine it with keypoint conditioning to create our human-specific multiview diffusion model, MEAT. In addition, we present valuable insights into applying multiview human motion videos for diffusion training, addressing the longstanding issue of data scarcity. Extensive experiments show that MEAT effectively generates dense, consistent multiview human images at the megapixel level, outperforming existing multiview diffusion methods.

Yushi Lan, Shangchen Zhou, Zhaoyang Lyu et al.

While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these challenges, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space. Our framework employs a Variational Autoencoder (VAE) with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information, and incorporates a cascaded latent flow-based model for improved shape-texture disentanglement. The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single image inputs. Notably, the newly proposed latent space naturally enables geometry-texture disentanglement, thus allowing 3D-aware editing. Experimental results demonstrate the effectiveness of our approach on multiple datasets, outperforming existing native 3D methods in both text- and image-conditioned 3D generation.

Wentao Wang, Hang Ye, Fangzhou Hong et al.

Given a single in-the-wild human photo, it remains a challenging task to reconstruct a high-fidelity 3D human model. Existing methods face difficulties including a) the varying body proportions captured by in-the-wild human images; b) diverse personal belongings within the shot; and c) ambiguities in human postures and inconsistency in human textures. In addition, the scarcity of high-quality human data intensifies the challenge. To address these problems, we propose a Generalizable image-to-3D huMAN reconstruction framework, dubbed GeneMAN, building upon a comprehensive multi-source collection of high-quality human data, including 3D scans, multi-view videos, single photos, and our generated synthetic human data. GeneMAN encompasses three key modules. 1) Without relying on parametric human models (e.g., SMPL), GeneMAN first trains a human-specific text-to-image diffusion model and a view-conditioned diffusion model, serving as GeneMAN 2D human prior and 3D human prior for reconstruction, respectively. 2) With the help of the pretrained human prior models, the Geometry Initialization-&-Sculpting pipeline is leveraged to recover high-quality 3D human geometry given a single image. 3) To achieve high-fidelity 3D human textures, GeneMAN employs the Multi-Space Texture Refinement pipeline, consecutively refining textures in the latent and the pixel spaces. Extensive experimental results demonstrate that GeneMAN could generate high-quality 3D human models from a single image input, outperforming prior state-of-the-art methods. Notably, GeneMAN could reveal much better generalizability in dealing with in-the-wild images, often yielding high-quality 3D human models in natural poses with common items, regardless of the body proportions in the input images.

Kaiyuan Xu, Fangzhou Hong, Daniel Elson et al.

Reconstructing surgical scenes from monocular endoscopic video is critical for advancing robotic-assisted surgery. However, the application of state-of-the-art general-purpose reconstruction models is constrained by two key challenges: the lack of supervised training data and performance degradation over long video sequences. To overcome these limitations, we propose SurgCUT3R, a systematic framework that adapts unified 3D reconstruction models to the surgical domain. Our contributions are threefold. First, we develop a data generation pipeline that exploits public stereo surgical datasets to produce large-scale, metric-scale pseudo-ground-truth depth maps, effectively bridging the data gap. Second, we propose a hybrid supervision strategy that couples our pseudo-ground-truth with geometric self-correction to enhance robustness against inherent data imperfections. Third, we introduce a hierarchical inference framework that employs two specialized models to effectively mitigate accumulated pose drift over long surgical videos: one for global stability and one for local accuracy. Experiments on the SCARED and StereoMIS datasets demonstrate that our method achieves a competitive balance between accuracy and efficiency, delivering near state-of-the-art but substantially faster pose estimation and offering a practical and effective solution for robust reconstruction in surgical environments. Project page: https://chumo-xu.github.io/SurgCUT3R-ICRA26/.

Ziang Cao, Fangzhou Hong, Zhaoxi Chen et al.

3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation properties, thereby limiting their utility in embodied AI. To bridge this gap, we introduce PhysX-Anything, the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes. Specifically, we propose the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry. It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets without introducing any special tokens during fine-tuning and significantly improving generative quality. In addition, to overcome the limited diversity of existing physical 3D datasets, we construct a new dataset, PhysX-Mobility, which expands the object categories in prior physical 3D datasets by over 2x and includes more than 2K common real-world objects with rich physical annotations. Extensive experiments on PhysX-Mobility and in-the-wild images demonstrate that PhysX-Anything delivers strong generative performance and robust generalization. Furthermore, simulation-based experiments in a MuJoCo-style environment validate that our sim-ready assets can be directly used for contact-rich robotic policy learning. We believe PhysX-Anything can substantially empower a broad range of downstream applications, especially in embodied AI and physics-based simulation.

Hao Li, Zhengyu Zou, Fangfu Liu et al.

Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions, enabling coherent and accurate understanding of complex scenes. However, most prior approaches prioritize training large geometry models for low-level 3D reconstruction and treat high-level spatial understanding in isolation, overlooking the crucial interplay between these two fundamental aspects of 3D-scene analysis, thereby limiting generalization and leading to poor performance in downstream 3D understanding tasks. Recent attempts have mitigated this issue by simply aligning 3D models with specific language models, thus restricting perception to the aligned model's capacity and limiting adaptability to downstream tasks. In this paper, we propose InstanceGrounded Geometry Transformer (IGGT), an end-to-end large unified transformer to unify the knowledge for both spatial reconstruction and instance-level contextual understanding. Specifically, we design a 3D-Consistent Contrastive Learning strategy that guides IGGT to encode a unified representation with geometric structures and instance-grounded clustering through only 2D visual inputs. This representation supports consistent lifting of 2D visual inputs into a coherent 3D scene with explicitly distinct object instances. To facilitate this task, we further construct InsScene-15K, a large-scale dataset with high-quality RGB images, poses, depth maps, and 3D-consistent instance-level mask annotations with a novel data curation pipeline.

Jingqiao Xiu, Fangzhou Hong, Yicong Li et al.

While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with the observed visual dynamics across adjacent video frames. To address these challenges, we propose EgoTwin, a joint video-motion generation framework built on the diffusion transformer architecture. Specifically, EgoTwin introduces a head-centric motion representation that anchors the human motion to the head joint and incorporates a cybernetics-inspired interaction mechanism that explicitly captures the causal interplay between video and motion within attention operations. For comprehensive evaluation, we curate a large-scale real-world dataset of synchronized text-video-motion triplets and design novel metrics to assess video-motion consistency. Extensive experiments demonstrate the effectiveness of the EgoTwin framework.

Haozhe Xie, Zhaoxi Chen, Fangzhou Hong et al.

3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However, adapting 3D-GS from finite-scale 3D objects and humans to infinite-scale 3D cities is non-trivial. Unbounded 3D city generation entails significant storage overhead (out-of-memory issues), arising from the need to expand points to billions, often demanding hundreds of Gigabytes of VRAM for a city scene spanning 10km^2. In this paper, we propose GaussianCity, a generative Gaussian Splatting framework dedicated to efficiently synthesizing unbounded 3D cities with a single feed-forward pass. Our key insights are two-fold: 1) Compact 3D Scene Representation: We introduce BEV-Point as a highly compact intermediate representation, ensuring that the growth in VRAM usage for unbounded scenes remains constant, thus enabling unbounded city generation. 2) Spatial-aware Gaussian Attribute Decoder: We present spatial-aware BEV-Point decoder to produce 3D Gaussian attributes, which leverages Point Serializer to integrate the structural and contextual characteristics of BEV points. Extensive experiments demonstrate that GaussianCity achieves state-of-the-art results in both drone-view and street-view 3D city generation. Notably, compared to CityDreamer, GaussianCity exhibits superior performance with a speedup of 60 times (10.72 FPS v.s. 0.18 FPS).

Tao Hu, Fangzhou Hong, Zhaoxi Chen et al.

We present FashionEngine, an interactive 3D human generation and editing system that creates 3D digital humans via user-friendly multimodal controls such as natural languages, visual perceptions, and hand-drawing sketches. FashionEngine automates the 3D human production with three key components: 1) A pre-trained 3D human diffusion model that learns to model 3D humans in a semantic UV latent space from 2D image training data, which provides strong priors for diverse generation and editing tasks. 2) Multimodality-UV Space encoding the texture appearance, shape topology, and textual semantics of human clothing in a canonical UV-aligned space, which faithfully aligns the user multimodal inputs with the implicit UV latent space for controllable 3D human editing. The multimodality-UV space is shared across different user inputs, such as texts, images, and sketches, which enables various joint multimodal editing tasks. 3) Multimodality-UV Aligned Sampler learns to sample high-quality and diverse 3D humans from the diffusion prior. Extensive experiments validate FashionEngine's state-of-the-art performance for conditional generation/editing tasks. In addition, we present an interactive user interface for our FashionEngine that enables both conditional and unconditional generation tasks, and editing tasks including pose/view/shape control, text-, image-, and sketch-driven 3D human editing and 3D virtual try-on, in a unified framework. Our project page is at: https://taohuumd.github.io/projects/FashionEngine.

Haozhe Xie, Zhaoxi Chen, Fangzhou Hong et al.

3D city generation is a desirable yet challenging task, since humans are more sensitive to structural distortions in urban environments. Additionally, generating 3D cities is more complex than 3D natural scenes since buildings, as objects of the same class, exhibit a wider range of appearances compared to the relatively consistent appearance of objects like trees in natural scenes. To address these challenges, we propose \textbf{CityDreamer}, a compositional generative model designed specifically for unbounded 3D cities. Our key insight is that 3D city generation should be a composition of different types of neural fields: 1) various building instances, and 2) background stuff, such as roads and green lands. Specifically, we adopt the bird's eye view scene representation and employ a volumetric render for both instance-oriented and stuff-oriented neural fields. The generative hash grid and periodic positional embedding are tailored as scene parameterization to suit the distinct characteristics of building instances and background stuff. Furthermore, we contribute a suite of CityGen Datasets, including OSM and GoogleEarth, which comprises a vast amount of real-world city imagery to enhance the realism of the generated 3D cities both in their layouts and appearances. CityDreamer achieves state-of-the-art performance not only in generating realistic 3D cities but also in localized editing within the generated cities.

Xinge Zhu, Hui Zhou, Tai Wang et al.

State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D convolution. Although this cooperation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the 3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties. The proposed model acts as a backbone and the learned features from this model can be used for downstream tasks such as point cloud semantic and panoptic segmentation or 3D detection. In this paper, we benchmark our model on these three tasks. For semantic segmentation, we evaluate the proposed model on several large-scale datasets, \ie, SemanticKITTI, nuScenes and A2D2. Our method achieves the state-of-the-art on the leaderboard of SemanticKITTI (both single-scan and multi-scan challenge), and significantly outperforms existing methods on nuScenes and A2D2 dataset. Furthermore, the proposed 3D framework also shows strong performance and good generalization on LiDAR panoptic segmentation and LiDAR 3D detection.

Fangzhou Hong, Hui Zhou, Xinge Zhu et al.

With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the objects (e.g. cars and pedestrians) or scenes (e.g. trees and buildings) from the LiDAR sensor. In this work, we address the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner. As one of the first endeavors towards this new challenging task, we propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. In particular, DS-Net has three appealing properties: 1) strong backbone design. DS-Net adopts the cylinder convolution that is specifically designed for LiDAR point clouds. The extracted features are shared by the semantic branch and the instance branch which operates in a bottom-up clustering style. 2) Dynamic Shifting for complex point distributions. We observe that commonly-used clustering algorithms like BFS or DBSCAN are incapable of handling complex autonomous driving scenes with non-uniform point cloud distributions and varying instance sizes. Thus, we present an efficient learnable clustering module, dynamic shifting, which adapts kernel functions on-the-fly for different instances. 3) Consensus-driven Fusion. Finally, consensus-driven fusion is used to deal with the disagreement between semantic and instance predictions. To comprehensively evaluate the performance of LiDAR-based panoptic segmentation, we construct and curate benchmarks from two large-scale autonomous driving LiDAR datasets, SemanticKITTI and nuScenes. Extensive experiments demonstrate that our proposed DS-Net achieves superior accuracies over current state-of-the-art methods. Notably, we achieve 1st place on the public leaderboard of SemanticKITTI, outperforming 2nd place by 2.6% in terms of the PQ metric.

Xinge Zhu, Hui Zhou, Tai Wang et al.

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern while maintaining these inherent properties. Moreover, a point-wise refinement module is introduced to alleviate the interference of lossy voxel-based label encoding. We evaluate the proposed model on two large-scale datasets, i.e., SemanticKITTI and nuScenes. Our method achieves the 1st place in the leaderboard of SemanticKITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%. Furthermore, the proposed 3D framework also generalizes well to LiDAR panoptic segmentation and LiDAR 3D detection.

Xinhai Liu, Zhizhong Han, Fangzhou Hong et al.

Learning discriminative feature directly on point clouds is still challenging in the understanding of 3D shapes. Recent methods usually partition point clouds into local region sets, and then extract the local region features with fixed-size CNN or MLP, and finally aggregate all individual local features into a global feature using simple max pooling. However, due to the irregularity and sparsity in sampled point clouds, it is hard to encode the fine-grained geometry of local regions and their spatial relationships when only using the fixed-size filters and individual local feature integration, which limit the ability to learn discriminative features. To address this issue, we present a novel Local-Region-Context Network (LRC-Net), to learn discriminative features on point clouds by encoding the fine-grained contexts inside and among local regions simultaneously. LRC-Net consists of two main modules. The first module, named intra-region context encoding, is designed for capturing the geometric correlation inside each local region by novel variable-size convolution filter. The second module, named inter-region context encoding, is proposed for integrating the spatial relationships among local regions based on spatial similarity measures. Experimental results show that LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.