Byungjun Kim (@byungjun__kim)
2025-12-22 | โค๏ธ 264 | ๐ 41
We introduce ๐๏ธ๐ ๐๐๐ฑ๐ญ๐๐ซ๐จ๐ฎ๐ฌ ๐๐จ๐ซ๐ฅ๐ ๐๐จ๐๐๐ฅ๐ฌ (๐๐๐) โ a scene-action-conditioned video diffusion model that simulates human manipulation in static 3D scenes from egocentric hand motions.
๐ Paper: https://arxiv.org/abs/2512.17907 ๐ Project Page: https://snuvclab.github.io/dwm/ https://x.com/byungjun__kim/status/2003171907454271775/video/1
๐ ์๋ณธ ๋งํฌ
- https://arxiv.org/abs/2512.17907
- https://snuvclab.github.io/dwm/
- https://x.com/byungjun__kim/status/2003171907454271775/video/1
๋ฏธ๋์ด
๐ Related
- objsplat-geometry-aware-gaussian-surfels-for-active-object
- gen3r-3d-scene-generation-meets-feed-forward-reconstruction
- gaussianfluent-explicit-gaussian-simulation-for-dynamic
- video-generation-but-4d-dynamic-scene-consistent-and-very
- gamo-geometry-aware-multi-view-diffusion-outpainting-for