HackerPapers

arXiv:2406.01056cs.CV

Virtual avatar generation models as world navigators

Sai Mandava

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

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.

arXiv comments
16 pages, 15 figures
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.AIArtificial Intelligence cs.HCHuman-Computer Interaction cs.LGMachine Learning cs.RORobotics

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jun 2024 to Jun 2024. Found in 1 HN submission from Jun 2024 to Jun 2024. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Virtual avatar generation models as world navigators 1 comment

    • We introduce 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…

      smandavaView on HNParent context

Submitted to Hacker News

  • Show HN: Research paper behind the AI climbing coach2 points1 comment

    Hi everyone. I've published the project page and paper for the AI climbing coach from a while back. Please check it out! Project page: https://virtual-avatar-generation.github.io/ Paper: https://arxiv.org/abs/2406.01056

Connected through shared HN threads, not inferred similarity or a recommendation.