Song-Hai Zhang

Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin et al.

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images.Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure consistency, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and reasonably good efficiency compared to prior works.

Xian Wu, Chen Wang, Hongbo Fu et al.

Researchers have explored various ways to generate realistic images from freehand sketches, e.g., for objects and human faces. However, how to generate realistic human body images from sketches is still a challenging problem. It is, first because of the sensitivity to human shapes, second because of the complexity of human images caused by body shape and pose changes, and third because of the domain gap between realistic images and freehand sketches. In this work, we present DeepPortraitDrawing, a deep generative framework for converting roughly drawn sketches to realistic human body images. To encode complicated body shapes under various poses, we take a local-to-global approach. Locally, we employ semantic part auto-encoders to construct part-level shape spaces, which are useful for refining the geometry of an input pre-segmented hand-drawn sketch. Globally, we employ a cascaded spatial transformer network to refine the structure of body parts by adjusting their spatial locations and relative proportions. Finally, we use a global synthesis network for the sketch-to-image translation task, and a face refinement network to enhance facial details. Extensive experiments have shown that given roughly sketched human portraits, our method produces more realistic images than the state-of-the-art sketch-to-image synthesis techniques.

Xin Yu, Yuan-Chen Guo, Yangguang Li et al.

Text-to-3D generation has made remarkable progress recently, particularly with methods based on Score Distillation Sampling (SDS) that leverages pre-trained 2D diffusion models. While the usage of classifier-free guidance is well acknowledged to be crucial for successful optimization, it is considered an auxiliary trick rather than the most essential component. In this paper, we re-evaluate the role of classifier-free guidance in score distillation and discover a surprising finding: the guidance alone is enough for effective text-to-3D generation tasks. We name this method Classifier Score Distillation (CSD), which can be interpreted as using an implicit classification model for generation. This new perspective reveals new insights for understanding existing techniques. We validate the effectiveness of CSD across a variety of text-to-3D tasks including shape generation, texture synthesis, and shape editing, achieving results superior to those of state-of-the-art methods. Our project page is https://xinyu-andy.github.io/Classifier-Score-Distillation

Zheng Chen, Chen Wang, Yuan-Chen Guo et al.

Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images. However, the geometry of NeRF is extremely under-constrained given sparse views, resulting in significant degradation of novel view synthesis quality. Inspired by self-supervised depth estimation methods, we propose StructNeRF, a solution to novel view synthesis for indoor scenes with sparse inputs. StructNeRF leverages the structural hints naturally embedded in multi-view inputs to handle the unconstrained geometry issue in NeRF. Specifically, it tackles the texture and non-texture regions respectively: a patch-based multi-view consistent photometric loss is proposed to constrain the geometry of textured regions; for non-textured ones, we explicitly restrict them to be 3D consistent planes. Through the dense self-supervised depth constraints, our method improves both the geometry and the view synthesis performance of NeRF without any additional training on external data. Extensive experiments on several real-world datasets demonstrate that StructNeRF surpasses state-of-the-art methods for indoor scenes with sparse inputs both quantitatively and qualitatively.

Yuan-Chen Guo, Yan-Pei Cao, Chen Wang et al.

With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level. Compared to traditional mesh-based assets, this volumetric representation is more powerful in expressing scene geometry but inevitably suffers from high rendering costs and can hardly be involved in further processes like editing, posing significant difficulties in combination with the existing graphics pipeline. In this paper, we present a hybrid volume-mesh representation, VMesh, which depicts an object with a textured mesh along with an auxiliary sparse volume. VMesh retains the advantages of mesh-based assets, such as efficient rendering, compact storage, and easy editing, while also incorporating the ability to represent subtle geometric structures provided by the volumetric counterpart. VMesh can be obtained from multi-view images of an object and renders at 2K 60FPS on common consumer devices with high fidelity, unleashing new opportunities for real-time immersive applications.

Zi-Xin Zou, Weihao Cheng, Yan-Pei Cao et al.

Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained diffusion priors into 3D representations using score distillation sampling (SDS), these methods often struggle to simultaneously achieve high-quality, consistent, and detailed results for both novel-view synthesis (NVS) and geometry. In this work, we present Sparse3D, a novel 3D reconstruction method tailored for sparse view inputs. Our approach distills robust priors from a multiview-consistent diffusion model to refine a neural radiance field. Specifically, we employ a controller that harnesses epipolar features from input views, guiding a pre-trained diffusion model, such as Stable Diffusion, to produce novel-view images that maintain 3D consistency with the input. By tapping into 2D priors from powerful image diffusion models, our integrated model consistently delivers high-quality results, even when faced with open-world objects. To address the blurriness introduced by conventional SDS, we introduce the category-score distillation sampling (C-SDS) to enhance detail. We conduct experiments on CO3DV2 which is a multi-view dataset of real-world objects. Both quantitative and qualitative evaluations demonstrate that our approach outperforms previous state-of-the-art works on the metrics regarding NVS and geometry reconstruction.

Cong Wang, Di Kang, Yan-Pei Cao et al.

Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, existing methods often struggle to model challenging facial regions (e.g., mouth interior, eyes, hair/beard), resulting in unrealistic and blurry results. In this paper, we propose {\fullname} ({\name}), a method that adopts the neural point representation as well as the neural volume rendering process and discards the predefined connectivity and hard correspondence imposed by mesh-based approaches. Specifically, the neural points are strategically constrained around the surface of the target expression via a high-resolution UV displacement map, achieving increased modeling capacity and more accurate control. We introduce three technical innovations to improve the rendering and training efficiency: a patch-wise depth-guided (shading point) sampling strategy, a lightweight radiance decoding process, and a Grid-Error-Patch (GEP) ray sampling strategy during training. By design, our {\name} is better equipped to handle topologically changing regions and thin structures while also ensuring accurate expression control when animating avatars. Experiments conducted on three subjects from the Multiface dataset demonstrate the effectiveness of our designs, outperforming previous state-of-the-art methods, especially in handling challenging facial regions.

Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai et al.

3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor capabilities. Therefore, contextual information across two consecutive frames is crucial for effective object tracking. However, points containing such useful information are often overlooked and cropped out in existing methods, leading to insufficient use of important contextual knowledge. To address this issue, we propose CXTrack, a novel transformer-based network for 3D object tracking, which exploits ConteXtual information to improve the tracking results. Specifically, we design a target-centric transformer network that directly takes point features from two consecutive frames and the previous bounding box as input to explore contextual information and implicitly propagate target cues. To achieve accurate localization for objects of all sizes, we propose a transformer-based localization head with a novel center embedding module to distinguish the target from distractors. Extensive experiments on three large-scale datasets, KITTI, nuScenes and Waymo Open Dataset, show that CXTrack achieves state-of-the-art tracking performance while running at 34 FPS.

Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo et al.

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements. However, synthesizing novel views from these panoramas remains a key challenge. Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with \emph{wide-baseline} panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection. Moreover, as some regions of the panorama are only visible from one view while invisible from others under wide baseline settings, PanoGRF incorporates $360^{\circ}$ monocular depth priors into spherical depth estimation to improve the geometry features. Experimental results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods for wide-baseline panoramas (e.g., OmniSyn) and perspective images (e.g., IBRNet, NeuRay).

Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai et al.

3D single object tracking has been a crucial problem for decades with numerous applications such as autonomous driving. Despite its wide-ranging use, this task remains challenging due to the significant appearance variation caused by occlusion and size differences among tracked targets. To address these issues, we present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme using Box Priors given in the first frame. Specifically, past frames with targetness masks serve as an external memory, and a transformer-based module propagates tracked target cues from the memory to the current frame. To precisely localize objects of all sizes, MBPTrack first predicts the target center via Hough voting. By leveraging box priors given in the first frame, we adaptively sample reference points around the target center that roughly cover the target of different sizes. Then, we obtain dense feature maps by aggregating point features into the reference points, where localization can be performed more effectively. Extensive experiments demonstrate that MBPTrack achieves state-of-the-art performance on KITTI, nuScenes and Waymo Open Dataset, while running at 50 FPS on a single RTX3090 GPU.

Tian-Xing Xu, Yuan-Chen Guo, Yong-Liang Yang et al.

Point clouds captured by depth sensors are often contaminated by noises, obstructing further analysis and applications. In this paper, we emphasize the importance of point distribution uniformity to downstream tasks. We demonstrate that point clouds produced by existing gradient-based denoisers lack uniformity despite having achieved promising quantitative results. To this end, we propose GPCD++, a gradient-based denoiser with an ultra-lightweight network named UniNet to address uniformity. Compared with previous state-of-the-art methods, our approach not only generates competitive or even better denoising results, but also significantly improves uniformity which largely benefits applications such as surface reconstruction.

Guan Luo, Xiu Li, Rui Chen et al.

The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A fundamental challenge limiting existing VAEs is the representation mismatch between ground-truth meshes and network predictions: GT meshes have arbitrary, variable topology, while VAEs typically predict fixed-structure implicit fields (\eg, SDF on regular grids). This inherent misalignment prevents establishing explicit mesh-level correspondences, forcing prior work to rely on indirect supervision signals such as SDF or rendering losses. Consequently, fine geometric details, particularly sharp features, are poorly preserved during reconstruction. To address this, we introduce TopoMesh, a sparse voxel-based VAE that unifies both GT and predicted meshes under a shared Dual Marching Cubes (DMC) topological framework. Specifically, we convert arbitrary input meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L$\infty$ distance metric. Our decoder outputs meshes in the same DMC format, ensuring that both predicted and target meshes share identical topological structures. This establishes explicit correspondences at the vertex and face level, allowing us to derive explicit mesh-level supervision signals for topology, vertex positions, and face orientations with clear gradients. Our sparse VAE architecture employs this unified framework and is trained with Teacher Forcing and progressive resolution training for stable and efficient convergence. Extensive experiments demonstrate that TopoMesh significantly outperforms existing VAEs in reconstruction fidelity, achieving superior preservation of sharp features and geometric details.

Guan Luo, Tian-Xing Xu, Ying-Tian Liu et al.

The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.

Chia-Hao Chen, Zi-Xin Zou, Yan-Pei Cao et al.

Generating high-fidelity, seamless textures directly on 3D surfaces, what we term 3D-native texturing, remains a fundamental open challenge, with the potential to overcome long-standing limitations of UV-based and multi-view projection methods. However, existing native approaches are constrained by the absence of a powerful and versatile latent representation, which severely limits the fidelity and generality of their generated textures. We identify this representation gap as the principal barrier to further progress. We introduce LaFiTe, a framework that addresses this challenge by learning to generate textures as a 3D generative sparse latent color field. At its core, LaFiTe employs a variational autoencoder (VAE) to encode complex surface appearance into a sparse, structured latent space, which is subsequently decoded into a continuous color field. This representation achieves unprecedented fidelity, exceeding state-of-the-art methods by >10 dB PSNR in reconstruction, by effectively disentangling texture appearance from mesh topology and UV parameterization. Building upon this strong representation, a conditional rectified-flow model synthesizes high-quality, coherent textures across diverse styles and geometries. Extensive experiments demonstrate that LaFiTe not only sets a new benchmark for 3D-native texturing but also enables flexible downstream applications such as material synthesis and texture super-resolution, paving the way for the next generation of 3D content creation workflows.

Zi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo et al.

Recent advancements in 3D reconstruction from single images have been driven by the evolution of generative models. Prominent among these are methods based on Score Distillation Sampling (SDS) and the adaptation of diffusion models in the 3D domain. Despite their progress, these techniques often face limitations due to slow optimization or rendering processes, leading to extensive training and optimization times. In this paper, we introduce a novel approach for single-view reconstruction that efficiently generates a 3D model from a single image via feed-forward inference. Our method utilizes two transformer-based networks, namely a point decoder and a triplane decoder, to reconstruct 3D objects using a hybrid Triplane-Gaussian intermediate representation. This hybrid representation strikes a balance, achieving a faster rendering speed compared to implicit representations while simultaneously delivering superior rendering quality than explicit representations. The point decoder is designed for generating point clouds from single images, offering an explicit representation which is then utilized by the triplane decoder to query Gaussian features for each point. This design choice addresses the challenges associated with directly regressing explicit 3D Gaussian attributes characterized by their non-structural nature. Subsequently, the 3D Gaussians are decoded by an MLP to enable rapid rendering through splatting. Both decoders are built upon a scalable, transformer-based architecture and have been efficiently trained on large-scale 3D datasets. The evaluations conducted on both synthetic datasets and real-world images demonstrate that our method not only achieves higher quality but also ensures a faster runtime in comparison to previous state-of-the-art techniques. Please see our project page at https://zouzx.github.io/TriplaneGaussian/.

Tianxing Xu, Zixuan Wang, Guangyuan Wang et al.

World models based on video generation demonstrate remarkable potential for simulating interactive environments but face persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-provided inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby constraining controllability and consistency. To address these limitations, we present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism. To reduce computational overhead, we design an efficient dual-stream diffusion transformer for high-fidelity generation. Moreover, we introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting, facilitating training on over 500K monocular videos. Extensive experiments on real-world and synthetic benchmarks demonstrate that UCM significantly outperforms state-of-the-art methods in long-term scene consistency, while also achieving precise camera controllability in high-fidelity video generation.

Ying-Tian Liu, Zhifei Zhang, Yuan-Chen Guo et al.

Automatic generation of fonts can be an important aid to typeface design. Many current approaches regard glyphs as pixelated images, which present artifacts when scaling and inevitable quality losses after vectorization. On the other hand, existing vector font synthesis methods either fail to represent the shape concisely or require vector supervision during training. To push the quality of vector font synthesis to the next level, we propose a novel dual-part representation for vector glyphs, where each glyph is modeled as a collection of closed "positive" and "negative" path pairs. The glyph contour is then obtained by boolean operations on these paths. We first learn such a representation only from glyph images and devise a subsequent contour refinement step to align the contour with an image representation to further enhance details. Our method, named DualVector, outperforms state-of-the-art methods in vector font synthesis both quantitatively and qualitatively. Our synthesized vector fonts can be easily converted to common digital font formats like TrueType Font for practical use. The code is released at https://github.com/thuliu-yt16/dualvector.

Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu et al.

Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multi-modal tasks and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention and branch attention; a related repository https://github.com/MenghaoGuo/Awesome-Vision-Attentions is dedicated to collecting related work. We also suggest future directions for attention mechanism research.

Tian-Xing Xu, Wenbo Hu, Yu-Kun Lai et al.

3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g. a single RTX 2080 Ti GPU.

Weicai Ye, Chenhao Ji, Zheng Chen et al.

Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses.

Ying-Tian Liu, Yuan-Chen Guo, Guan Luo et al.

Diffusion models trained on large-scale text-image datasets have demonstrated a strong capability of controllable high-quality image generation from arbitrary text prompts. However, the generation quality and generalization ability of 3D diffusion models is hindered by the scarcity of high-quality and large-scale 3D datasets. In this paper, we present PI3D, a framework that fully leverages the pre-trained text-to-image diffusion models' ability to generate high-quality 3D shapes from text prompts in minutes. The core idea is to connect the 2D and 3D domains by representing a 3D shape as a set of Pseudo RGB Images. We fine-tune an existing text-to-image diffusion model to produce such pseudo-images using a small number of text-3D pairs. Surprisingly, we find that it can already generate meaningful and consistent 3D shapes given complex text descriptions. We further take the generated shapes as the starting point for a lightweight iterative refinement using score distillation sampling to achieve high-quality generation under a low budget. PI3D generates a single 3D shape from text in only 3 minutes and the quality is validated to outperform existing 3D generative models by a large margin.

Cong Wang, Di Kang, He-Yi Sun et al.

Creating high-fidelity head avatars from multi-view videos is a core issue for many AR/VR applications. However, existing methods usually struggle to obtain high-quality renderings for all different head components simultaneously since they use one single representation to model components with drastically different characteristics (e.g., skin vs. hair). In this paper, we propose a Hybrid Mesh-Gaussian Head Avatar (MeGA) that models different head components with more suitable representations. Specifically, we select an enhanced FLAME mesh as our facial representation and predict a UV displacement map to provide per-vertex offsets for improved personalized geometric details. To achieve photorealistic renderings, we obtain facial colors using deferred neural rendering and disentangle neural textures into three meaningful parts. For hair modeling, we first build a static canonical hair using 3D Gaussian Splatting. A rigid transformation and an MLP-based deformation field are further applied to handle complex dynamic expressions. Combined with our occlusion-aware blending, MeGA generates higher-fidelity renderings for the whole head and naturally supports more downstream tasks. Experiments on the NeRSemble dataset demonstrate the effectiveness of our designs, outperforming previous state-of-the-art methods and supporting various editing functionalities, including hairstyle alteration and texture editing.

Yunhan Yang, Yukun Huang, Xiaoyang Wu et al.

Utilizing pre-trained 2D large-scale generative models, recent works are capable of generating high-quality novel views from a single in-the-wild image. However, due to the lack of information from multiple views, these works encounter difficulties in generating controllable novel views. In this paper, we present DreamComposer, a flexible and scalable framework that can enhance existing view-aware diffusion models by injecting multi-view conditions. Specifically, DreamComposer first uses a view-aware 3D lifting module to obtain 3D representations of an object from multiple views. Then, it renders the latent features of the target view from 3D representations with the multi-view feature fusion module. Finally the target view features extracted from multi-view inputs are injected into a pre-trained diffusion model. Experiments show that DreamComposer is compatible with state-of-the-art diffusion models for zero-shot novel view synthesis, further enhancing them to generate high-fidelity novel view images with multi-view conditions, ready for controllable 3D object reconstruction and various other applications.

Tian-Xing Xu, Xiangjun Gao, Wenbo Hu et al.

Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that learns a latent space agnostic to video latent distributions for effective point map encoding and decoding. Leveraging the VAE, we train a video diffusion model to model the distribution of point map sequences conditioned on the input videos. Extensive evaluations on diverse datasets demonstrate that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.

Zheng Chen, Chenming Wu, Zhelun Shen et al.

Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs. However, synthesizing novel views from these panoramic images in real time remains a significant challenge, especially due to panoramic imagery's high resolution and inherent distortions. Although existing 3D Gaussian splatting (3DGS) methods can produce photo-realistic views under narrow baselines, they often overfit the training views when dealing with wide-baseline panoramic images due to the difficulty in learning precise geometry from sparse 360$^{\circ}$ views. This paper presents \textit{Splatter-360}, a novel end-to-end generalizable 3DGS framework designed to handle wide-baseline panoramic images. Unlike previous approaches, \textit{Splatter-360} performs multi-view matching directly in the spherical domain by constructing a spherical cost volume through a spherical sweep algorithm, enhancing the network's depth perception and geometry estimation. Additionally, we introduce a 3D-aware bi-projection encoder to mitigate the distortions inherent in panoramic images and integrate cross-view attention to improve feature interactions across multiple viewpoints. This enables robust 3D-aware feature representations and real-time rendering capabilities. Experimental results on the HM3D~\cite{hm3d} and Replica~\cite{replica} demonstrate that \textit{Splatter-360} significantly outperforms state-of-the-art NeRF and 3DGS methods (e.g., PanoGRF, MVSplat, DepthSplat, and HiSplat) in both synthesis quality and generalization performance for wide-baseline panoramic images. Code and trained models are available at \url{https://3d-aigc.github.io/Splatter-360/}.

Yue-Jiang Dong, Yuan-Chen Guo, Ying-Tian Liu et al.

Self-supervised monocular depth estimation is of significant importance with applications spanning across autonomous driving and robotics. However, the reliance on self-supervision introduces a strong static-scene assumption, thereby posing challenges in achieving optimal performance in dynamic scenes, which are prevalent in most real-world situations. To address these issues, we propose PPEA-Depth, a Progressive Parameter-Efficient Adaptation approach to transfer a pre-trained image model for self-supervised depth estimation. The training comprises two sequential stages: an initial phase trained on a dataset primarily composed of static scenes, succeeded by an expansion to more intricate datasets involving dynamic scenes. To facilitate this process, we design compact encoder and decoder adapters to enable parameter-efficient tuning, allowing the network to adapt effectively. They not only uphold generalized patterns from pre-trained image models but also retain knowledge gained from the preceding phase into the subsequent one. Extensive experiments demonstrate that PPEA-Depth achieves state-of-the-art performance on KITTI, CityScapes and DDAD datasets.

Yue-Jiang Dong, Fang-Lue Zhang, Song-Hai Zhang

Depth perception is crucial for a wide range of robotic applications. Multi-frame self-supervised depth estimation methods have gained research interest due to their ability to leverage large-scale, unlabeled real-world data. However, the self-supervised methods often rely on the assumption of a static scene and their performance tends to degrade in dynamic environments. To address this issue, we present Motion-Aware Loss, which leverages the temporal relation among consecutive input frames and a novel distillation scheme between the teacher and student networks in the multi-frame self-supervised depth estimation methods. Specifically, we associate the spatial locations of moving objects with the temporal order of input frames to eliminate errors induced by object motion. Meanwhile, we enhance the original distillation scheme in multi-frame methods to better exploit the knowledge from a teacher network. MAL is a novel, plug-and-play module designed for seamless integration into multi-frame self-supervised monocular depth estimation methods. Adding MAL into previous state-of-the-art methods leads to a reduction in depth estimation errors by up to 4.2% and 10.8% on KITTI and CityScapes benchmarks, respectively.

Heyi Sun, Cong Wang, Tian-Xing Xu et al.

Creating high-fidelity and editable head avatars is a pivotal challenge in computer vision and graphics, boosting many AR/VR applications. While recent advancements have achieved photorealistic renderings and plausible animation, head editing, especially real-time appearance editing, remains challenging due to the implicit representation and entangled modeling of the geometry and global appearance. To address this, we propose Surface-Volumetric Gaussian Head Avatar (SVG-Head), a novel hybrid representation that explicitly models the geometry with 3D Gaussians bound on a FLAME mesh and leverages disentangled texture images to capture the global appearance. Technically, it contains two types of Gaussians, in which surface Gaussians explicitly model the appearance of head avatars using learnable texture images, facilitating real-time texture editing, while volumetric Gaussians enhance the reconstruction quality of non-Lambertian regions (e.g., lips and hair). To model the correspondence between 3D world and texture space, we provide a mesh-aware Gaussian UV mapping method, which leverages UV coordinates given by the FLAME mesh to obtain sharp texture images and real-time rendering speed. A hierarchical optimization strategy is further designed to pursue the optimal performance in both reconstruction quality and editing flexibility. Experiments on the NeRSemble dataset show that SVG-Head not only generates high-fidelity rendering results, but also is the first method to obtain explicit texture images for Gaussian head avatars and support real-time appearance editing.

Yue-Jiang Dong, Wang Zhao, Jiale Xu et al.

Diffusion-based video depth estimation methods have achieved remarkable success with strong generalization ability. However, predicting depth for long videos remains challenging. Existing methods typically split videos into overlapping sliding windows, leading to accumulated scale discrepancies across different windows, particularly as the number of windows increases. Additionally, these methods rely solely on 2D diffusion priors, overlooking the inherent 3D geometric structure of video depths, which results in geometrically inconsistent predictions. In this paper, we propose DepthSync, a novel, training-free framework using diffusion guidance to achieve scale- and geometry-consistent depth predictions for long videos. Specifically, we introduce scale guidance to synchronize the depth scale across windows and geometry guidance to enforce geometric alignment within windows based on the inherent 3D constraints in video depths. These two terms work synergistically, steering the denoising process toward consistent depth predictions. Experiments on various datasets validate the effectiveness of our method in producing depth estimates with improved scale and geometry consistency, particularly for long videos.

Ying-Tian Liu, Yuan-Chen Guo, Song-Hai Zhang

Is the center position fully capable of representing a pixel? There is nothing wrong to represent pixels with their centers in a discrete image representation, but it makes more sense to consider each pixel as the aggregation of signals from a local area in an image super-resolution (SR) context. Despite the great capability of coordinate-based implicit representation in the field of arbitrary-scale image SR, this area's nature of pixels is not fully considered. To this end, we propose integrated positional encoding (IPE), extending traditional positional encoding by aggregating frequency information over the pixel area. We apply IPE to the state-of-the-art arbitrary-scale image super-resolution method: local implicit image function (LIIF), presenting IPE-LIIF. We show the effectiveness of IPE-LIIF by quantitative and qualitative evaluations, and further demonstrate the generalization ability of IPE to larger image scales and multiple implicit-based methods. Code will be released.

Chen Wang, Xian Wu, Yuan-Chen Guo et al.

We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs. Our method is built upon Neural Radiance Fields (NeRF) that predicts per-point density and color with a multi-layer perceptron. While producing images at arbitrary scales, NeRF struggles with resolutions that go beyond observed images. Our key insight is that NeRF benefits from 3D consistency, which means an observed pixel absorbs information from nearby views. We first exploit it by a supersampling strategy that shoots multiple rays at each image pixel, which further enforces multi-view constraint at a sub-pixel level. Then, we show that NeRF-SR can further boost the performance of supersampling by a refinement network that leverages the estimated depth at hand to hallucinate details from related patches on only one HR reference image. Experiment results demonstrate that NeRF-SR generates high-quality results for novel view synthesis at HR on both synthetic and real-world datasets without any external information.

Yuan-Chen Guo, Di Kang, Linchao Bao et al.

Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle simple reflections like highlights but cannot deal with complex reflections such as those from glass and mirrors. In these scenarios, NeRF models the virtual image as real geometries which leads to inaccurate depth estimation, and produces blurry renderings when the multi-view consistency is violated as the reflected objects may only be seen under some of the viewpoints. To overcome these issues, we introduce NeRFReN, which is built upon NeRF to model scenes with reflections. Specifically, we propose to split a scene into transmitted and reflected components, and model the two components with separate neural radiance fields. Considering that this decomposition is highly under-constrained, we exploit geometric priors and apply carefully-designed training strategies to achieve reasonable decomposition results. Experiments on various self-captured scenes show that our method achieves high-quality novel view synthesis and physically sound depth estimation results while enabling scene editing applications.

Yuan Xue, Yuan-Chen Guo, Han Zhang et al.

In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross pollination between major image generation paradigms, and evaluation and comparison of generation methods.

Ying-Tian Liu, Yuan-Chen Guo, Yi-Xiao Li et al.

In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Experiments on font reconstruction and interpolation tasks verified that this structured implicit representation is suitable for describing both structure and style features of glyphs. Furthermore, based on the proposed representation, we design a simple yet effective disentangled network for the challenging one-shot font style transfer problem, and achieve the best results comparing to state-of-the-art alternatives in both quantitative and qualitative comparisons. Benefit from this representation, our generated glyphs have the potential to be converted to vector fonts through post-processing, reducing the gap between rasterized images and vector graphics. We hope this work can provide a powerful tool for 2D shape analysis and synthesis, and inspire further exploitation in implicit representations for 2D shape modeling.

Tian-Xing Xu, Yuan-Chen Guo, Zhiqiang Li et al.

Place recognition plays an essential role in the field of autonomous driving and robot navigation. Point cloud based methods mainly focus on extracting global descriptors from local features of point clouds. Despite having achieved promising results, existing solutions neglect the following aspects, which may cause performance degradation: (1) huge size difference between objects in outdoor scenes; (2) moving objects that are unrelated to place recognition; (3) long-range contextual information. We illustrate that the above aspects bring challenges to extracting discriminative global descriptors. To mitigate these problems, we propose a novel method named TransLoc3D, utilizing adaptive receptive fields with a point-wise reweighting scheme to handle objects of different sizes while suppressing noises, and an external transformer to capture long-range feature dependencies. As opposed to existing architectures which adopt fixed and limited receptive fields, our method benefits from size-adaptive receptive fields as well as global contextual information, and outperforms current state-of-the-arts with significant improvements on popular datasets.

Song-Hai Zhang, Yuan-Chen Guo, Qing-Wen Gu

We investigate the problem of generating 3D meshes from single free-hand sketches, aiming at fast 3D modeling for novice users. It can be regarded as a single-view reconstruction problem, but with unique challenges, brought by the variation and conciseness of sketches. Ambiguities in poorly-drawn sketches could make it hard to determine how the sketched object is posed. In this paper, we address the importance of viewpoint specification for overcoming such ambiguities, and propose a novel view-aware generation approach. By explicitly conditioning the generation process on a given viewpoint, our method can generate plausible shapes automatically with predicted viewpoints, or with specified viewpoints to help users better express their intentions. Extensive evaluations on various datasets demonstrate the effectiveness of our view-aware design in solving sketch ambiguities and improving reconstruction quality.

Miao Wang, Guo-Ye Yang, Ruilong Li et al.

Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to implicit characteristics of images, for example: in portraits "style" includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes, it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar.

Song-Hai Zhang, Zhengping Zhou, Bin Liu et al.

In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes. A bounding box for the inserted object is predicted in both tasks, which helps downstream applications such as semi-automated advertising and video composition. The major challenge lies in the fact that the target object is neither present nor localized at test time, whereas available datasets only provide scenes with existing objects. To tackle this problem, we build an unsupervised algorithm based on object-level contexts, which explicitly models the joint probability distribution of object categories and bounding boxes with a Gaussian mixture model. Experiments on our newly annotated test set demonstrate that our system outperforms existing baselines on all subtasks, and do so under a unified framework. Our contribution promises future extensions and applications.

Dun Liang, Yuanchen Guo, Shaokui Zhang et al.

High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. And the maps can be constructed precisely even with inaccurate crowdsourced data.

Song-Hai Zhang, Ruilong Li, Xin Dong et al.

The standard approach to image instance segmentation is to perform the object detection first, and then segment the object from the detection bounding-box. More recently, deep learning methods like Mask R-CNN perform them jointly. However, little research takes into account the uniqueness of the "human" category, which can be well defined by the pose skeleton. Moreover, the human pose skeleton can be used to better distinguish instances with heavy occlusion than using bounding-boxes. In this paper, we present a brand new pose-based instance segmentation framework for humans which separates instances based on human pose, rather than proposal region detection. We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion. Furthermore, there are few public datasets containing many heavily occluded humans along with comprehensive annotations, which makes this a challenging problem seldom noticed by researchers. Therefore, in this paper we introduce a new benchmark "Occluded Human (OCHuman)", which focuses on occluded humans with comprehensive annotations including bounding-box, human pose and instance masks. This dataset contains 8110 detailed annotated human instances within 4731 images. With an average 0.67 MaxIoU for each person, OCHuman is the most complex and challenging dataset related to human instance segmentation. Through this dataset, we want to emphasize occlusion as a challenging problem for researchers to study.