GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

作者：Weikang Bian, Zhaoyang Huang, Xiaoyu Shi, Yijin Li, Fu-Yun Wang, Hongsheng Li · 单位：Multimedia Laboratory, The Chinese University of Hong Kong, Multimedia Laboratory, The Chinese University of Hong Kong, Centre for Perceptual and Interactive Intelligence 3Avolution AI · 会议/期刊：arXiv preprint · 发布日期：2025-01-05