2000 character limit reached
Virtual avatar generation models as world navigators (2406.01056v1)
Published 3 Jun 2024 in cs.CV, cs.AI, cs.HC, cs.LG, and cs.RO
Abstract: We introduce SABR-CLIMB, a novel video model simulating human movement in rock climbing environments using a virtual avatar. Our diffusion transformer predicts the sample instead of noise in each diffusion step and ingests entire videos to output complete motion sequences. By leveraging a large proprietary dataset, NAV-22M, and substantial computational resources, we showcase a proof of concept for a system to train general-purpose virtual avatars for complex tasks in robotics, sports, and healthcare.