概念
Image-to-Video Inpainting Model
A class of pretrained models capable of generating or completing video sequences conditioned on a single image frame and motion conditions. In this work it is used to synthesize videos with geometric distortions.
Timeline (last 90 days)
Oct 19
The construction pipeline of the VG-Pairs synthetic paired supervision dataset is: starting from real videos with diverse camera motion and pose annotations, treating each video clip as a 'geometrically consistent target', and then using a pretrained image-to-video restoration model with trajectory-adaptive keyframes to synthesize the corresponding 'distorted version'.
Unverified50%