AI RESEARCH
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
arXiv CS.LG
•
ArXi:2601.23286v2 Announce Type: replace-cross While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we