Bringing foundation models to depth sensing: DeFM is trained on 60M depth images with self-supervised learning to captur

Bringing foundation models to depth sensing: DeFM is trained on 60M depth images with self-supervised learning to capture geometry and semantics, preserve metric awareness, distill into compact models, and set SOTA in sim-to-real robotics. https://x.com/robotsdigest/status/2016491151268966750/video/1

🔗 원본 링크

• https://x.com/robotsdigest/status/2016491151268966750/video/1

미디어