4 papers
SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
Chengjie Hong, Feixiang He, Yiheng Zeng +2
We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential for reducing memory use and ac…
A Step to Decouple Optimization in 3DGS
Renjie Ding, Yaonan Wang, Min Liu +6
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time novel view synthesis. As an explicit representation optimized through gradient propagation among prim…
3D Student Splatting and Scooping
Jialin Zhu, Jiangbei Yue, Feixiang He +1
Recently, 3D Gaussian Splatting (3DGS) provides a new framework for novel view synthesis, and has spiked a new wave of research in neural rendering and related applications. As 3DG…
Learning Extremely High Density Crowds as Active Matters
Feixiang He, Jiangbei Yue, Jialin Zhu +4
Video-based high-density crowd analysis and prediction has been a long-standing topic in computer vision. It is notoriously difficult due to, but not limited to, the lack of high-q…