This repository contains the model described in ORV: 4D Occupancy-centric Robot Video Generation.
The model is an image-to-video generation model for robot manipulation, based on CogVideoX and trained with action and occupancy-derived guidance.
This repository contains the model described in ORV: 4D Occupancy-centric Robot Video Generation.
The model is an image-to-video generation model for robot manipulation, based on CogVideoX and trained with action and occupancy-derived guidance.