Zhizhong Su

Xuewu Lin, Zixiang Pei, Tianwei Lin et al.

In autonomous driving perception systems, 3D detection and tracking are the two fundamental tasks. This paper delves deeper into this field, building upon the Sparse4D framework. We introduce two auxiliary training tasks (Temporal Instance Denoising and Quality Estimation) and propose decoupled attention to make structural improvements, leading to significant enhancements in detection performance. Additionally, we extend the detector into a tracker using a straightforward approach that assigns instance ID during inference, further highlighting the advantages of query-based algorithms. Extensive experiments conducted on the nuScenes benchmark validate the effectiveness of the proposed improvements. With ResNet50 as the backbone, we witnessed enhancements of 3.0\%, 2.2\%, and 7.6\% in mAP, NDS, and AMOTA, achieving 46.9\%, 56.1\%, and 49.0\%, respectively. Our best model achieved 71.9\% NDS and 67.7\% AMOTA on the nuScenes test set. Code will be released at \url{https://github.com/linxuewu/Sparse4D}.

Xuewu Lin, Tianwei Lin, Zixiang Pei et al.

Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task. Comparing with BEV based methods, sparse based methods lag behind in performance, but still have lots of non-negligible merits. To push sparse 3D detection further, in this work, we introduce a novel method, named Sparse4D, which does the iterative refinement of anchor boxes via sparsely sampling and fusing spatial-temporal features. (1) Sparse 4D Sampling: for each 3D anchor, we assign multiple 4D keypoints, which are then projected to multi-view/scale/timestamp image features to sample corresponding features; (2) Hierarchy Feature Fusion: we hierarchically fuse sampled features of different view/scale, different timestamp and different keypoints to generate high-quality instance feature. In this way, Sparse4D can efficiently and effectively achieve 3D detection without relying on dense view transformation nor global attention, and is more friendly to edge devices deployment. Furthermore, we introduce an instance-level depth reweight module to alleviate the ill-posed issue in 3D-to-2D projection. In experiment, our method outperforms all sparse based methods and most BEV based methods on detection task in the nuScenes dataset.

Haoyi Jiang, Liu Liu, Xinjie Wang et al.

While Vision-Language Models (VLMs) exhibit exceptional 2D visual understanding, their ability to comprehend and reason about 3D space--a cornerstone of spatial intelligence--remains superficial. Current methodologies attempt to bridge this domain gap either by relying on explicit 3D modalities or by augmenting VLMs with partial, view-conditioned geometric priors. However, such approaches hinder scalability and ultimately burden the language model with the ill-posed task of implicitly reconstructing holistic 3D geometry from sparse cues. In this paper, we argue that spatial intelligence can emerge inherently from 2D vision alone, rather than being imposed via explicit spatial instruction tuning. To this end, we introduce Spa3R, a self-supervised framework that learns a unified, view-invariant spatial representation directly from unposed multi-view images. Spa3R is built upon the proposed Predictive Spatial Field Modeling (PSFM) paradigm, where Spa3R learns to synthesize feature fields for arbitrary unseen views conditioned on a compact latent representation, thereby internalizing a holistic and coherent understanding of the underlying 3D scene. We further integrate the pre-trained Spa3R Encoder into existing VLMs via a lightweight adapter to form Spa3-VLM, effectively grounding language reasoning in a global spatial context. Experiments on the challenging VSI-Bench demonstrate that Spa3-VLM achieves state-of-the-art accuracy of 58.6% on 3D VQA, significantly outperforming prior methods. These results highlight PSFM as a scalable path toward advancing spatial intelligence. Code is available at https://github.com/hustvl/Spa3R.

Jiazhi Yang, Kunyang Lin, Jinwei Li et al.

Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation tasks, where minor execution deviations can compound into failures. While reinforcement learning (RL) offers a principled path to robustness, on-policy RL in the physical world is constrained by safety risk, hardware cost, and environment reset. To bridge this gap, we present RISE, a scalable framework of robotic reinforcement learning via imagination. At its core is a Compositional World Model that (i) predicts multi-view future via a controllable dynamics model, and (ii) evaluates imagined outcomes with a progress value model, producing informative advantages for the policy improvement. Such compositional design allows state and value to be tailored by best-suited yet distinct architectures and objectives. These components are integrated into a closed-loop self-improving pipeline that continuously generates imaginary rollouts, estimates advantages, and updates the policy in imaginary space without costly physical interaction. Across three challenging real-world tasks, RISE yields significant improvement over prior art, with more than +35% absolute performance increase in dynamic brick sorting, +45% for backpack packing, and +35% for box closing, respectively.

Haoyi Jiang, Liu Liu, Tianheng Cheng et al.

3D Semantic Occupancy Prediction is fundamental for spatial understanding, yet existing approaches face challenges in scalability and generalization due to their reliance on extensive labeled data and computationally intensive voxel-wise representations. In this paper, we introduce GaussTR, a novel Gaussian-based Transformer framework that unifies sparse 3D modeling with foundation model alignment through Gaussian representations to advance 3D spatial understanding. GaussTR predicts sparse sets of Gaussians in a feed-forward manner to represent 3D scenes. By splatting the Gaussians into 2D views and aligning the rendered features with foundation models, GaussTR facilitates self-supervised 3D representation learning and enables open-vocabulary semantic occupancy prediction without requiring explicit annotations. Empirical experiments on the Occ3D-nuScenes dataset demonstrate GaussTR's state-of-the-art zero-shot performance of 12.27 mIoU, along with a 40% reduction in training time. These results highlight the efficacy of GaussTR for scalable and holistic 3D spatial understanding, with promising implications in autonomous driving and embodied agents. The code is available at https://github.com/hustvl/GaussTR.

Shuo Wang, Yucheng Wang, Guoxin Lian et al.

Vision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they have advanced within a multi-step instruction. However, recent Vision-Language-Action models focus on direct action prediction and earlier progress methods predict numeric achievements; both overlook the monotonic co-progression property of the observation and instruction sequences. Building on this insight, Progress-Think introduces semantic progress reasoning, predicting instruction-style progress from visual observations to enable more accurate navigation. To achieve this without expensive annotations, we propose a three-stage framework. In the initial stage, Self-Aligned Progress Pretraining bootstraps a reasoning module via a novel differentiable alignment between visual history and instruction prefixes. Then, Progress-Guided Policy Pretraining injects learned progress states into the navigation context, guiding the policy toward consistent actions. Finally, Progress-Policy Co-Finetuning jointly optimizes both modules with tailored progress-aware reinforcement objectives. Experiments on R2R-CE and RxR-CE show state-of-the-art success and efficiency, demonstrating that semantic progress yields a more consistent representation of navigation advancement.

Maiyue Chen, Kaihui Wang, Bo Zhang et al.

In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1 is to scale control-policy training with a large-scale hybrid motion corpus, where video-reconstructed motions from in-the-wild videos provide the dominant source of motion diversity, while curated motion-capture and in-house motion data provide higher-fidelity supervision and deployment-oriented coverage. This data regime enables HoloMotion-1 to move beyond conventional MoCap-only training and exposes the policy to substantially broader behaviors, capture conditions, and motion styles. Learning from such heterogeneous data introduces new challenges, including reconstruction noise, source-domain mismatch, uneven motion quality, and the need for temporal modeling under large behavioral variation. To address these challenges, HoloMotion-1 integrates large-capacity temporal modeling, a sparsely activated Mixture-of-Experts Transformer with KV-cache inference for real-time control, and a sequence-level training strategy that improves learning efficiency on extended motion sequences. Extensive experiments on multiple unseen motion benchmarks show that HoloMotion-1 generalizes robustly across diverse motion types and capture conditions, significantly improves tracking accuracy over prior methods, and transfers directly to a real humanoid robot without task-specific fine-tuning.

Xiangyu Sun, Haoyi Jiang, Liu Liu et al.

Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic understanding from reconstruction or necessitate costly per-scene optimization, thereby restricting their scalability and generalizability. In this paper, we introduce Uni3R, a novel feed-forward framework that jointly reconstructs a unified 3D scene representation enriched with open-vocabulary semantics, directly from unposed multi-view images. Our approach leverages a Cross-View Transformer to robustly integrate information across arbitrary multi-view inputs, which then regresses a set of 3D Gaussian primitives endowed with semantic feature fields. This unified representation facilitates high-fidelity novel view synthesis, open-vocabulary 3D semantic segmentation, and depth prediction, all within a single, feed-forward pass. Extensive experiments demonstrate that Uni3R establishes a new state-of-the-art across multiple benchmarks, including 25.07 PSNR on RE10K and 55.84 mIoU on ScanNet. Our work signifies a novel paradigm towards generalizable, unified 3D scene reconstruction and understanding. The code is available at https://github.com/HorizonRobotics/Uni3R.

Xinjie Wang, Liu Liu, Yu Cao et al.

Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low cost accessibility and affordability of 3D data assets are critical for achieving generalization and scalability in embodied AI. However, most current embodied intelligence tasks still rely heavily on traditional 3D computer graphics assets manually created and annotated, which suffer from high production costs and limited realism. These limitations significantly hinder the scalability of data driven approaches. We present EmbodiedGen, a foundational platform for interactive 3D world generation. It enables the scalable generation of high-quality, controllable and photorealistic 3D assets with accurate physical properties and real-world scale in the Unified Robotics Description Format (URDF) at low cost. These assets can be directly imported into various physics simulation engines for fine-grained physical control, supporting downstream tasks in training and evaluation. EmbodiedGen is an easy-to-use, full-featured toolkit composed of six key modules: Image-to-3D, Text-to-3D, Texture Generation, Articulated Object Generation, Scene Generation and Layout Generation. EmbodiedGen generates diverse and interactive 3D worlds composed of generative 3D assets, leveraging generative AI to address the challenges of generalization and evaluation to the needs of embodied intelligence related research. Code is available at https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html.

Guoxin Lian, Shuo Wang, Yucheng Wang et al.

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that maps should instead be learned representations shaped directly by navigation objectives rather than exhaustive reconstructions. Based on this insight, we propose MapDream, a map-in-the-loop framework that formulates map construction as autoregressive bird's-eye-view (BEV) image synthesis. The framework jointly learns map generation and action prediction, distilling environmental context into a compact three-channel BEV map that preserves only navigation-critical affordances. Supervised pre-training bootstraps a reliable mapping-to-control interface, while the autoregressive design enables end-to-end joint optimization through reinforcement fine-tuning. Experiments on R2R-CE and RxR-CE achieve state-of-the-art monocular performance, validating task-driven generative map learning.

Andrew Choi, Xinjie Wang, Zhizhong Su et al.

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs directly in the real world to avoid addressing the sim-to-real gap. While real-world RL circumvents sim-to-real issues, it inherently limits the generality of the resulting VLA, as scaling scene and object diversity in the physical world is prohibitively difficult. This leads to the paradoxical outcome of transforming a broadly pretrained model into an overfitted, scene-specific policy. Training in simulation can instead provide access to diverse scenes, but designing those scenes is also costly. In this work, we show that VLAs can be RL fine-tuned without sacrificing generality and with reduced labor by leveraging 3D world generative models. Using these models together with a language-driven scene designer, we generate hundreds of diverse interactive scenes containing unique objects and backgrounds, enabling scalable and highly parallel policy learning. Starting from a pretrained imitation baseline, our approach increases simulation success from 9.7% to 79.8% while achieving a 1.25$\times$ speedup in task completion time. We further demonstrate successful sim-to-real transfer enabled by the quality of the generated digital twins together with domain randomization, improving real-world success from 21.7% to 75% and achieving a 1.13$\times$ speedup. Finally, we further highlight the benefits of leveraging the effectively unlimited data from 3D world generative models through an ablation study showing that increasing scene diversity directly improves zero-shot generalization.

Ze-Xin Yin, Jiaxiong Qiu, Liu Liu et al.

The labor- and experience-intensive creation of 3D assets with physically based rendering (PBR) materials demands an autonomous 3D asset creation pipeline. However, most existing 3D generation methods focus on geometry modeling, either baking textures into simple vertex colors or leaving texture synthesis to post-processing with image diffusion models. To achieve end-to-end PBR-ready 3D asset generation, we present Lightweight Gaussian Asset Adapter (LGAA), a novel framework that unifies the modeling of geometry and PBR materials by exploiting multi-view (MV) diffusion priors from a novel perspective. The LGAA features a modular design with three components. Specifically, the LGAA Wrapper reuses and adapts network layers from MV diffusion models, which encapsulate knowledge acquired from billions of images, enabling better convergence in a data-efficient manner. To incorporate multiple diffusion priors for geometry and PBR synthesis, the LGAA Switcher aligns multiple LGAA Wrapper layers encapsulating different knowledge. Then, a tamed variational autoencoder (VAE), termed LGAA Decoder, is designed to predict 2D Gaussian Splatting (2DGS) with PBR channels. Finally, we introduce a dedicated post-processing procedure to effectively extract high-quality, relightable mesh assets from the resulting 2DGS. Extensive quantitative and qualitative experiments demonstrate the superior performance of LGAA with both text-and image-conditioned MV diffusion models. Additionally, the modular design enables flexible incorporation of multiple diffusion priors, and the knowledge-preserving scheme leads to efficient convergence trained on merely 69k multi-view instances. Our code, pre-trained weights, and the dataset used will be publicly available via our project page: https://zx-yin.github.io/dreamlifting/.

Tingyang Xiao, Xiaolin Zhou, Liu Liu et al.

This paper presents GeoFlow-SLAM, a robust and effective Tightly-Coupled RGBD-inertial SLAM for legged robotics undergoing aggressive and high-frequency motions.By integrating geometric consistency, legged odometry constraints, and dual-stream optical flow (GeoFlow), our method addresses three critical challenges:feature matching and pose initialization failures during fast locomotion and visual feature scarcity in texture-less scenes.Specifically, in rapid motion scenarios, feature matching is notably enhanced by leveraging dual-stream optical flow, which combines prior map points and poses. Additionally, we propose a robust pose initialization method for fast locomotion and IMU error in legged robots, integrating IMU/Legged odometry, inter-frame Perspective-n-Point (PnP), and Generalized Iterative Closest Point (GICP). Furthermore, a novel optimization framework that tightly couples depth-to-map and GICP geometric constraints is first introduced to improve the robustness and accuracy in long-duration, visually texture-less environments. The proposed algorithms achieve state-of-the-art (SOTA) on collected legged robots and open-source datasets. To further promote research and development, the open-source datasets and code will be made publicly available at https://github.com/HorizonRobotics/GeoFlowSlam

Xuewu Lin, Tianwei Lin, Zixiang Pei et al.

Sparse algorithms offer great flexibility for multi-view temporal perception tasks. In this paper, we present an enhanced version of Sparse4D, in which we improve the temporal fusion module by implementing a recursive form of multi-frame feature sampling. By effectively decoupling image features and structured anchor features, Sparse4D enables a highly efficient transformation of temporal features, thereby facilitating temporal fusion solely through the frame-by-frame transmission of sparse features. The recurrent temporal fusion approach provides two main benefits. Firstly, it reduces the computational complexity of temporal fusion from $O(T)$ to $O(1)$, resulting in significant improvements in inference speed and memory usage. Secondly, it enables the fusion of long-term information, leading to more pronounced performance improvements due to temporal fusion. Our proposed approach, Sparse4Dv2, further enhances the performance of the sparse perception algorithm and achieves state-of-the-art results on the nuScenes 3D detection benchmark. Code will be available at \url{https://github.com/linxuewu/Sparse4D}.

Shaobo Guo, Xiao Jiang, Zhizhong Su et al.

As a critical cue for understanding human intention, human gaze provides a key signal for Human-Computer Interaction(HCI) applications. Appearance-based gaze estimation, which directly regresses the gaze vector from eye images, has made great progress recently based on Convolutional Neural Networks(ConvNets) architecture and open-source large-scale gaze datasets. However, encoding model-based knowledge into CNN model to further improve the gaze estimation performance remains a topic that needs to be explored. In this paper, we propose HybridGazeNet(HGN), a unified framework that encodes the geometric eyeball model into the appearance-based CNN architecture explicitly. Composed of a multi-branch network and an uncertainty module, HybridGazeNet is trained using a hyridized strategy. Experiments on multiple challenging gaze datasets shows that HybridGazeNet has better accuracy and generalization ability compared with existing SOTA methods. The code will be released later.

Mengjia Yan, Mengao Zhao, Zining Xu et al.

To improve the discriminative and generalization ability of lightweight network for face recognition, we propose an efficient variable group convolutional network called VarGFaceNet. Variable group convolution is introduced by VarGNet to solve the conflict between small computational cost and the unbalance of computational intensity inside a block. We employ variable group convolution to design our network which can support large scale face identification while reduce computational cost and parameters. Specifically, we use a head setting to reserve essential information at the start of the network and propose a particular embedding setting to reduce parameters of fully-connected layer for embedding. To enhance interpretation ability, we employ an equivalence of angular distillation loss to guide our lightweight network and we apply recursive knowledge distillation to relieve the discrepancy between the teacher model and the student model. The champion of deepglint-light track of LFR (2019) challenge demonstrates the effectiveness of our model and approach. Implementation of VarGFaceNet will be released at https://github.com/zma-c-137/VarGFaceNet soon.

Liu Liu, Xiaofeng Wang, Guosheng Zhao et al.

Imitation Learning has become a fundamental approach in robotic manipulation. However, collecting large-scale real-world robot demonstrations is prohibitively expensive. Simulators offer a cost-effective alternative, but the sim-to-real gap make it extremely challenging to scale. Therefore, we introduce RoboTransfer, a diffusion-based video generation framework for robotic data synthesis. Unlike previous methods, RoboTransfer integrates multi-view geometry with explicit control over scene components, such as background and object attributes. By incorporating cross-view feature interactions and global depth/normal conditions, RoboTransfer ensures geometry consistency across views. This framework allows fine-grained control, including background edits and object swaps. Experiments demonstrate that RoboTransfer is capable of generating multi-view videos with enhanced geometric consistency and visual fidelity. In addition, policies trained on the data generated by RoboTransfer achieve a 33.3% relative improvement in the success rate in the DIFF-OBJ setting and a substantial 251% relative improvement in the more challenging DIFF-ALL scenario. Explore more demos on our project page: https://horizonrobotics.github.io/robot_lab/robotransfer

Hongzhe Bi, Lingxuan Wu, Tianwei Lin et al.

Imitation learning for robotic manipulation faces a fundamental challenge: the scarcity of large-scale, high-quality robot demonstration data. Recent robotic foundation models often pre-train on cross-embodiment robot datasets to increase data scale, while they face significant limitations as the diverse morphologies and action spaces across different robot embodiments make unified training challenging. In this paper, we present H-RDT (Human to Robotics Diffusion Transformer), a novel approach that leverages human manipulation data to enhance robot manipulation capabilities. Our key insight is that large-scale egocentric human manipulation videos with paired 3D hand pose annotations provide rich behavioral priors that capture natural manipulation strategies and can benefit robotic policy learning. We introduce a two-stage training paradigm: (1) pre-training on large-scale egocentric human manipulation data, and (2) cross-embodiment fine-tuning on robot-specific data with modular action encoders and decoders. Built on a diffusion transformer architecture with 2B parameters, H-RDT uses flow matching to model complex action distributions. Extensive evaluations encompassing both simulation and real-world experiments, single-task and multitask scenarios, as well as few-shot learning and robustness assessments, demonstrate that H-RDT outperforms training from scratch and existing state-of-the-art methods, including Pi0 and RDT, achieving significant improvements of 13.9% and 40.5% over training from scratch in simulation and real-world experiments, respectively. The results validate our core hypothesis that human manipulation data can serve as a powerful foundation for learning bimanual robotic manipulation policies.

Jiaxiong Qiu, Liu Liu, Xinjie Wang et al.

Recently, 3D Gaussian Splatting (3DGS) has achieved impressive performance on indoor surface reconstruction and 3D open-vocabulary segmentation. This paper presents GLS, a unified framework of 3D surface reconstruction and open-vocabulary segmentation based on 3DGS. GLS extends two fields by improving their sharpness and smoothness. For indoor surface reconstruction, we introduce surface normal prior as a geometric cue to guide the rendered normal, and use the normal error to optimize the rendered depth. For 3D open-vocabulary segmentation, we employ 2D CLIP features to guide instance features and enhance the surface smoothness, then utilize DEVA masks to maintain their view consistency. Extensive experiments demonstrate the effectiveness of jointly optimizing surface reconstruction and 3D open-vocabulary segmentation, where GLS surpasses state-of-the-art approaches of each task on MuSHRoom, ScanNet++ and LERF-OVS datasets. Project webpage: https://jiaxiongq.github.io/GLS_ProjectPage.

Shuo Wang, Yongcai Wang, Zhaoxin Fan et al.

Vision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents.

Xuewu Lin, Tianwei Lin, Lichao Huang et al.

A key challenge in robot manipulation lies in developing policy models with strong spatial understanding, the ability to reason about 3D geometry, object relations, and robot embodiment. Existing methods often fall short: 3D point cloud models lack semantic abstraction, while 2D image encoders struggle with spatial reasoning. To address this, we propose SEM (Spatial Enhanced Manipulation model), a novel diffusion-based policy framework that explicitly enhances spatial understanding from two complementary perspectives. A spatial enhancer augments visual representations with 3D geometric context, while a robot state encoder captures embodiment-aware structure through graphbased modeling of joint dependencies. By integrating these modules, SEM significantly improves spatial understanding, leading to robust and generalizable manipulation across diverse tasks that outperform existing baselines.

Xuewu Lin, Tianwei Lin, Lichao Huang et al.

In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric information, still constrain perception performance due to inherent sparsity, noise, and data scarcity. In this work, we introduce a novel image-centric 3D perception model, BIP3D, which leverages expressive image features with explicit 3D position encoding to overcome the limitations of point-centric methods. Specifically, we leverage pre-trained 2D vision foundation models to enhance semantic understanding, and introduce a spatial enhancer module to improve spatial understanding. Together, these modules enable BIP3D to achieve multi-view, multi-modal feature fusion and end-to-end 3D perception. In our experiments, BIP3D outperforms current state-of-the-art results on the EmbodiedScan benchmark, achieving improvements of 5.69% in the 3D detection task and 15.25% in the 3D visual grounding task.

Ze-Xin Yin, Liu Liu, Xinjie Wang et al.

Compositional 3D scene generation from a single view requires the simultaneous recovery of scene layout and 3D assets. Existing approaches mainly fall into two categories: feed-forward generation methods and per-instance generation methods. The former directly predict 3D assets with explicit 6DoF poses through efficient network inference, but they generalize poorly to complex scenes. The latter improve generalization through a divide-and-conquer strategy, but suffer from time-consuming pose optimization. To bridge this gap, we introduce 3D-Fixer, a novel in-place completion paradigm. Specifically, 3D-Fixer extends 3D object generative priors to generate complete 3D assets conditioned on the partially visible point cloud at the original locations, which are cropped from the fragmented geometry obtained from the geometry estimation methods. Unlike prior works that require explicit pose alignment, 3D-Fixer uses fragmented geometry as a spatial anchor to preserve layout fidelity. At its core, we propose a coarse-to-fine generation scheme to resolve boundary ambiguity under occlusion, supported by a dual-branch conditioning network and an Occlusion-Robust Feature Alignment (ORFA) strategy for stable training. Furthermore, to address the data scarcity bottleneck, we present ARSG-110K, the largest scene-level dataset to date, comprising over 110K diverse scenes and 3M annotated images with high-fidelity 3D ground truth. Extensive experiments show that 3D-Fixer achieves state-of-the-art geometric accuracy, which significantly outperforms baselines such as MIDI and Gen3DSR, while maintaining the efficiency of the diffusion process. Code and data will be publicly available at https://zx-yin.github.io/3dfixer.

Hongzhe Bi, Hengkai Tan, Shenghao Xie et al.

While a general embodied agent must function as a unified system, current methods are built on isolated models for understanding, world modeling, and control. This fragmentation prevents unifying multimodal generative capabilities and hinders learning from large-scale, heterogeneous data. In this paper, we propose Motus, a unified latent action world model that leverages existing general pretrained models and rich, sharable motion information. Motus introduces a Mixture-of-Transformer (MoT) architecture to integrate three experts (i.e., understanding, video generation, and action) and adopts a UniDiffuser-style scheduler to enable flexible switching between different modeling modes (i.e., world models, vision-language-action models, inverse dynamics models, video generation models, and video-action joint prediction models). Motus further leverages the optical flow to learn latent actions and adopts a recipe with three-phase training pipeline and six-layer data pyramid, thereby extracting pixel-level "delta action" and enabling large-scale action pretraining. Experiments show that Motus achieves superior performance against state-of-the-art methods in both simulation (a +15% improvement over X-VLA and a +45% improvement over Pi0.5) and real-world scenarios(improved by +11~48%), demonstrating unified modeling of all functionalities and priors significantly benefits downstream robotic tasks.

Liu Liu, Xinjie Wang, Jiaxiong Qiu et al.

3D scene reconstruction is a foundational problem in computer vision. Despite recent advancements in Neural Implicit Representations (NIR), existing methods often lack editability and compositional flexibility, limiting their use in scenarios requiring high interactivity and object-level manipulation. In this paper, we introduce the Gaussian Object Carver (GOC), a novel, efficient, and scalable framework for object-compositional 3D scene reconstruction. GOC leverages 3D Gaussian Splatting (GS), enriched with monocular geometry priors and multi-view geometry regularization, to achieve high-quality and flexible reconstruction. Furthermore, we propose a zero-shot Object Surface Completion (OSC) model, which uses 3D priors from 3d object data to reconstruct unobserved surfaces, ensuring object completeness even in occluded areas. Experimental results demonstrate that GOC improves reconstruction efficiency and geometric fidelity. It holds promise for advancing the practical application of digital twins in embodied AI, AR/VR, and interactive simulation environments.

Tingyang Xiao, Liu Liu, Wei Feng et al.

Geometry foundation models have significantly advanced dense geometric SLAM, yet existing systems often lack deep semantic understanding and robust loop closure capabilities. Meanwhile, contemporary semantic mapping approaches are frequently hindered by decoupled architectures and fragile data association. We propose IRIS-SLAM, a novel RGB semantic SLAM system that leverages unified geometric-instance representations derived from an instance-extended foundation model. By extending a geometry foundation model to concurrently predict dense geometry and cross-view consistent instance embeddings, we enable a semantic-synergized association mechanism and instance-guided loop closure detection. Our approach effectively utilizes viewpoint-agnostic semantic anchors to bridge the gap between geometric reconstruction and open-vocabulary mapping. Experimental results demonstrate that IRIS-SLAM significantly outperforms state-of-the-art methods, particularly in map consistency and wide-baseline loop closure reliability.

Wenhao Hu, Zesheng Li, Haonan Zhou et al.

Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan often fail to capture the full structural details. Existing approaches typically rely on multi stage pipelines, such as segmentation, background completion, and inpainting or require per-object dense scanning, both of which are error-prone, and not easily scalable. We propose IGFuse, a novel framework that reconstructs interactive Gaussian scene by fusing observations from multiple scans, where natural object rearrangement between captures reveal previously occluded regions. Our method constructs segmentation aware Gaussian fields and enforces bi-directional photometric and semantic consistency across scans. To handle spatial misalignments, we introduce a pseudo-intermediate scene state for unified alignment, alongside collaborative co-pruning strategies to refine geometry. IGFuse enables high fidelity rendering and object level scene manipulation without dense observations or complex pipelines. Extensive experiments validate the framework's strong generalization to novel scene configurations, demonstrating its effectiveness for real world 3D reconstruction and real-to-simulation transfer. Our project page is available online.

Yunrui Yu, Hang Su, Cheng-zhong Xu et al.

Gradient-based adversarial attacks using the Cross-Entropy (CE) loss often suffer from overestimation due to relative errors in gradient computation induced by floating-point arithmetic. This paper provides a rigorous theoretical analysis of these errors, conducting the first comprehensive study of floating-point computation errors in gradient-based attacks across four distinct scenarios: (i) unsuccessful untargeted attacks, (ii) successful untargeted attacks, (iii) unsuccessful targeted attacks, and (iv) successful targeted attacks. We establish theoretical foundations characterizing the behavior of relative numerical errors under different attack conditions, revealing previously unknown patterns in gradient computation instability, and identify floating-point underflow and rounding as key contributors. Building on this insight, we propose the Theoretical MIFPE (T-MIFPE) loss function, which incorporates an optimal scaling factor $T = t^*$ to minimize the impact of floating-point errors, thereby enhancing the accuracy of gradient computation in adversarial attacks. Extensive experiments on the MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate that T-MIFPE outperforms existing loss functions, including CE, C\&W, DLR, and MIFPE, in terms of attack potency and robustness evaluation accuracy.

Yilin Xiong, Zijian Zhou, Yuhao Dou et al.

Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate regression methods and heatmap based methods. However, the former loses spatial information, resulting in poor performance while the latter suffers from large output size or high post-processing complexity. This paper proposes a new solution, Gaussian Vector, to preserve the spatial information as well as reduce the output size and simplify the post-processing. Our method provides novel vector supervision and introduces Band Pooling Module to convert heatmap into a pair of vectors for each landmark. This is a plug-and-play component which is simple and effective. Moreover, Beyond Box Strategy is proposed to handle the landmarks out of the face bounding box. We evaluate our method on 300W, COFW, WFLW and JD-landmark. That the results significantly surpass previous works demonstrates the effectiveness of our approach.

Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes et al.

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate mean-field approximate inference for the Conditional Random Fields with Gaussian pairwise potentials as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.