Gang Zeng

Peking University — China

Computer Science · Physical Sciences

32h-index5.3kcitations110works3.82yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(36), Advanced Image and Video Retrieval Techniques(33), Computer Graphics and Visualization Techniques(23), 3D Shape Modeling and Analysis(22), Advanced Neural Network Applications(21)

Publications110 total

Generating Objects with Part-Articulation from a Single Image
2025· 1 citedOpen Access
Fast SP-GS: Reconstructing Dynamic Scenes in Minutes
2025
DreamArt: Generating Interactable Articulated Objects from a Single Image
arXiv (Cornell University)·2025Open Access
Efficient Part-level 3D Object Generation via Dual Volume Packing
arXiv (Cornell University)·2025Open Access
MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
2025· 1 cited
Real-Time Neural Radiance Talking Portrait Synthesis via Audio-Spatial Decomposition
International Journal of Computer Vision·2025· 21 cited
VolGen: Volumetric Latent Diffusion Models for 3D Object Generation
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025
MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes
arXiv (Cornell University)·2024Open Access
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
arXiv (Cornell University)·2024Open Access
RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting
Lecture notes in computer science·2024· 2 cited
EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
arXiv (Cornell University)·2024· 3 citedOpen Access
Open-set Hierarchical Semantic Segmentation for 3D Scene
2024· 1 cited
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
2024· 35 cited
Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
arXiv (Cornell University)·2024Open Access
RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting
arXiv (Cornell University)·2024Open Access
InTeX: Interactive Text-to-texture Synthesis via Unified Depth-aware Inpainting
arXiv (Cornell University)·2024Open Access
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
2024· 1 cited
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
arXiv (Cornell University)·2023· 4 citedOpen Access
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
2023· 172 cited
Context Autoencoder for Self-supervised Representation Learning
International Journal of Computer Vision·2023· 274 cited
page 1 of 6Next →

Frequent Co-authors

Jingdong Wang(19), Xiaokang Chen(15), Long Quan(10), Shipeng Li(6), Rui Gan(6), Hongbin Zha(6), Jingbo Wang(5), Kwan-Yee Lin(4), Hongsheng Li(4), Ping Tan(4), Sing Bing Kang(4), Falong Shen(4), Jiaxiang Tang(4), Yajie Xing(4), Luc Van Gool(3), Shuicheng Yan(3), Jing Wang(3), Yuhui Yuan(2), Pascal Müller(2), Peter Wonka(2)