UGG unifies video generation and 4D geometric prediction
One model treats RGB, depth, and camera pose as conditional completion and can search scene hypotheses at inference.
Stories per day · 30 days
Relateddepth-estimation2video-generation24d-perception14d-scenes1generative-models1lora1point-tracking1
2 stories, newest first · one card per story
Stories tagged #camera-pose
Gen4P: Video Generators are 4D Perceivers
Gen4P turns a pretrained video generator into a single-pass 4D perceiver for tracking, depth, and pose.