About Me

I am currently pursuing my Master’s degree at Nanjing University, where I have the privilege of working with Prof. Yao Yao, Prof. Hao Zhu, and Prof. Xun Cao. I received my Bachelor’s degree from Xidian University in 2023.

My research interests lie at the intersection of 3D computer vision, computer graphics, and generative models—with a particular focus on representing and generatively modeling 3D and 4D objects.

Publications

STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians

Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao
ECCV 2024
Arxiv / Project Page
Leveraging multiview diffusion to generate consistent 4D objects in a creative way.

AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation

Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao
Arxiv 2023
Arxiv / Project Page
Personalize diffusion model for avatar generation with specific ID.

Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

Shuang Wu, Youtian Lin, Feihu Zhang, Yifei Zeng, Jingxi Xu, Philip Torr, Xun Cao, Yao Yao
NeurIPS 2024
Arxiv / Project Page
3D Native DiT for sharp mesh generation.

Direct3D S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Shuang Wu, Youtian Lin, Feihu Zhang, Yifei Zeng, Yikang Yang, Yajie Bao, Jiachen Qian, Siyu Zhu, Xun Cao, Philip Torr, Yao Yao
Arxiv 2025
Arxiv / Project Page
Sparse attention for 3D generation, enabling 1024³ sparse voxel resolution.

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Yanwen Wang, Yiyu Zhuang, Jiawei Zhang, Li Wang, Yifei Zeng, Xun Cao, Xinxin Zuo, Hao Zhu
ICCV 2025
Paper
Generating avatar in UV space efficiently with gaussian attribute map.