Reproduce “UniCaMo: Unified Camera and Motion Control for Video Diffusion Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Long Vu, Tan Ngo, Animesh Karnewar, Amir Habibian, Binh-Son Hua, Hung Bui, Minh Hoai Nguyen, Phong Nguyen
UniCaMo controls video generation by encoding 3D object trajectories and camera motion in the initial noise. It propagates noise through 3D views, using a persistent spherical noise field for regions without correspondences; this guides synthesis but does not reconstruct unseen geometry. On 300 joint-control clips, it reports an EPE of 2.95 versus 3.28 for SymphoMotion, with results limited to the evaluated setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.