Video Generative Models as Geometry Learner
This work repurposes pretrained video generative models as a unified and data-efficient framework for geometry estimation, formulated innovatively as a next-frames prediction task, and inherits naturally structured knowledge and richer priors from the video model, enabling more data efficient and effective learning of geometry.
Haosen Yang, Jifei Song, Zhensong Zhang et al.
· 0 citations