@byungjun__kim
We introduce šļøš ššš±ššš«šØš®š¬ ššØš«š„š ššØššš„š¬ (ššš) ā a scene-action-conditioned video diffusion model that simulates human manipulation in static 3D scenes from egocentric hand motions. š Paper: https://t.co/u2IldpfYTD š Project Page: https://t.co/YSE3rOmV1s https://t.co/mYrjUdO5aJ