EgoMo3R: Stanford's NeurIPS paper jointly reconstructs 3D motion and scenes from egocentric video
jcniebles · x · 2026-11-09
A Stanford–Panasonic team presents EgoMo3R (NeurIPS 2026), a joint optimization framework that reconstructs 3D human motion and scene geometry from casual egocentric video. It combines monocular depth, optical flow, and point tracks with a diffusion-based human motion prior via alternating first-order optimization: scene reconstruction grounds the motion prior, while the prior regularizes camera trajectories and anchors the scene in a metric, gravity-aligned frame. It outperforms specialized baselines on dynamic EgoExo4D and Nymeria sequences, targeting AR/VR and robotics.
More from Embodied
- Agent Buddy: an ESP32 animated companion that shows your AI coding agents' live status — DanWahlin · 2026-11-09
- Origami Robotics to Unveil New Direct-Drive Robot Hands and Data Glove at CoRL Party — ybisk · 2026-11-09
- OmniGuide steers diffusion VLAs at test time with differentiable 3D guidance, no retraining — thoma_gu · 2026-11-09
- Physical Intelligence to present π0.7 at CoRL oral with emergent robot capabilities — lucy_x_shi · 2026-11-09
- Fully open MolmoAct2 action reasoning model wins Best Paper at CoRL TAG — jmin__cho · 2026-11-09
- Dyna Robotics' Dynasaur Folds Clothes Nonstop at CoRL, Shrugging Off Every Interruption — JasonMa2020 · 2026-11-09