AI RESEARCH
ReFlow: Self-correction Motion Learning for Dynamic Scene Reconstruction
arXiv CS.CV
•
ArXi:2604.01561v1 Announce Type: new We present ReFlow, a unified framework for monocular dynamic scene reconstruction that learns 3D motion in a novel self-correction manner from raw video. Existing methods often suffer from incomplete scene initialization for dynamic regions, leading to unstable reconstruction and motion estimation, which often resorts to external dense motion guidance such as pre-computed optical flow to further stabilize and constrain the reconstruction of dynamic components. However, this