1 citations · 2 across the 10 of their papers we have counts for
11 papers
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
Zhengwentai Sun, Keru Zheng, Chenghong Li +7
Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods…
ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
Yuantao Chen, Jiahao Chang, Chongjie Ye +4
The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild vide…
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…
MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis
Yihao Zhi, Chenghong Li, Hongjie Liao +6
Recent breakthroughs in video generation, powered by large-scale datasets and diffusion techniques, have shown that video diffusion models can function as implicit 4D novel view sy…
MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization
Chenghong Li, Hongjie Liao, Yihao Zhi +5
In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while…
Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage
Zhengwentai Sun, Chenghong Li, Hongjie Liao +7
Achieving fine-grained controllability in human image synthesis is a long-standing challenge in computer vision. Existing methods primarily focus on either facial synthesis or near…
GarVerseLOD: High-Fidelity 3D Garment Reconstruction from a Single In-the-Wild Image using a Dataset with Levels of Details
Zhongjin Luo, Haolin Liu, Chenghong Li +6
Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress,…
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures
Zhangyang Xiong, Chenghong Li, Kenkun Liu +9
In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while…
EMS: 3D Eyebrow Modeling from Single-view Images
Chenghong Li, Leyang Jin, Yujian Zheng +2
Eyebrows play a critical role in facial expression and appearance. Although the 3D digitization of faces is well explored, less attention has been drawn to 3D eyebrow modeling. In…
PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis
Xianggang Yu, Jiapeng Tang, Yipeng Qin +4
We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely…
Fully Attentional Network for Semantic Segmentation
Qi Song, Jie Li, Chenghong Li +2
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of R…