Check out the exciting papers led by my students Umangi Jain and Ziyi Wu in this morning's #NeurIPS2024 poster session. Their work is impressive! 1/🧵
Comments
Log in with your Bluesky account to leave a comment
Ziyi's work in image diffusion models proposes to use a set of per-object representations to control the 3D pose of individual objects in a scene. It was done during an internship with Thomas Kipf's amazing team at DeepMind 2/🧵
Umangi proposes an approach for segmentation in scenes created with 3D Gaussian Splatting (3DGS). It avoids changing the underlying optimization process, achieving a speedup over existing 3DGS segmentation methods. end/🧵
Comments
East Exhibit Hall A-C 1507
Project: https://neural-assets.github.io/
Poster: East Exhibit Hall A-C 1303
Project: https://umangi-jain.github.io/gaussiancut/