Profiles2022-2026
Ziyang Song
University of Wisconsin-Madison
5Papers
0Last author
5Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- MV-S2V: Multi-View Subject-Consistent Video GenerationAuthor 1 of 4SIGGRAPH 2026 · 1 citation
- TRACE: Learning 3D Gaussian Physical Dynamics from Multi-View VideosAuthor 2 of 3ICCV 2025 · 3 citations
- FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian VelocityAuthor 2 of 4CVPR 2025
- NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic VideosAuthor 2 of 3NeurIPS 2023 · 39 citations
- OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point CloudsAuthor 1 of 2NeurIPS 2022 · 41 citations
