action transfer 1cross-shadow prediction 1interactive video control 1shadow representation 1video world models 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Jin Cao, Zian Meng, Kaipeng Zhang
ShadowDancer introduces a method for precise, frame‑level control of video world models by learning unified dynamics representations from paired videos that share the same underlyi…
cs.CV2025
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Jianhong Bai, Menghan Xia, Xiao Fu +8
Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite…