26 citations · 39 across the 17 of their papers we have counts for
19 papers
TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation
Ziteng Lu, Yushuang Wu, Chongjie Ye +7
High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing representat…
UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents
Xufan He, Yushuang Wu, Xiaoyang Guo +5
Part-level 3D generation is essential for applications requiring decomposable and structured 3D synthesis. However, existing methods either rely on implicit part segmentation with…
ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
Jiahao Chang, Chongjie Ye, Yushuang Wu +6
Existing multi-view 3D object reconstruction methods heavily rely on sufficient overlap between input views, where occlusions and sparse coverage in practice frequently yield sever…
Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion
Mutian Xu, Chongjie Ye, Haolin Liu +3
3D data simulation aims to bridge the gap between simulated and real-captured 3D data, which is a fundamental problem for real-world 3D visual tasks. Most 3D data simulation method…
Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging
Chongjie Ye, Yushuang Wu, Ziteng Lu +5
With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due…
MVImgNet2.0: A Larger-scale Dataset of Multi-view Images
Xiaoguang Han, Yushuang Wu, Luyue Shi +7
MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via mult…
DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors
Zizheng Yan, Jiapeng Zhou, Fanpeng Meng +6
Text-to-3D generation has recently seen significant progress. To enhance its practicality in real-world applications, it is crucial to generate multiple independent objects with in…
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
Chongjie Ye, Lingteng Qiu, Xiaodong Gu +6
This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized…
IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images
Yushuang Wu, Luyue Shi, Junhao Cai +6
Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transfo…
RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
Lingteng Qiu, Guanying Chen, Xiaodong Gu +7
Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric prior and the complex entanglement of materials and lighting in natural images. Existin…
Efficient View Synthesis with Neural Radiance Distribution Field
Yushuang Wu, Xiao Li, Jinglu Wang +3
Recent work on Neural Radiance Fields (NeRF) has demonstrated significant advances in high-quality view synthesis. A major limitation of NeRF is its low rendering efficiency due to…
Universal Semi-supervised Model Adaptation via Collaborative Consistency Training
Zizheng Yan, Yushuang Wu, Yipeng Qin +3
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained sou…
SCoDA: Domain Adaptive Shape Completion for Real Scans
Yushuang Wu, Zizheng Yan, Ce Chen +6
3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing…
MVImgNet: A Large-scale Dataset of Multi-view Images
Xianggang Yu, Mutian Xu, Yidan Zhang +10
Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer…
A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective
Chaoqi Chen, Yushuang Wu, Qiyuan Dai +5
Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (\emph{e.g.,} social…
PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images
Zhangyang Xiong, Dong Du, Yushuang Wu +4
It is very challenging to accurately reconstruct sophisticated human geometry caused by various poses and garments from a single image. Recently, works based on pixel-aligned impli…
Multi-level Consistency Learning for Semi-supervised Domain Adaptation
Zizheng Yan, Yushuang Wu, Guanbin Li +3
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-l…
PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds
Yushuang Wu, Zizheng Yan, Shengcai Cai +4
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervi…
3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
Yuda Qiu, Xiaojie Xu, Lingteng Qiu +4
Caricature is an artistic representation that deliberately exaggerates the distinctive features of a human face to convey humor or sarcasm. However, reconstructing a 3D caricature…