Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

arXiv:2307.00574v4 Announce Type: replace
Abstract: We introduce a method to generate temporally coherent human animation from a single image, a video, or a random noise. This problem has been formulated as modeling of an auto-regressive generation, i.e., to regress past frames to decode future frames. However, such unidirectional generation is highly prone to motion drifting over time, generating unrealistic human animation with significant artifacts such as appearance distortion. We claim that bidirectional temporal modeling enforces temporal coherence on a generative …

abstract animation arxiv auto consistent cs.cv decode diffusion diffusion model future generate however human image modeling noise random temporal type video