Gen4P: Video Generators are 4D Perceivers
Gen4P turns a pretrained video generator into a single-pass 4D perceiver for tracking, depth, and pose.
3 stories, newest first · one card per story
Gen4P turns a pretrained video generator into a single-pass 4D perceiver for tracking, depth, and pose.
TrackEverything tracks all visible 3D points in videos beyond 1,000 frames within 40 GB by de-duplicating scene geometry.
TrackEverything densely tracks all visible 3D points beyond 1000 frames within 40 GB, beating dense trackers by over 20% APD.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views