EgoXperience: Single-Pass Joint Reconstruction of Camera, Scene, Hands and Objects from Egocentric Video
ropedia-ai · hf · 2026-10-20
Ropedia with NTU, Tsinghua and PKU introduce EgoXperience, a unified framework for learning world-grounded egocentric representations, with data, models, and code open-sourced.
- A single-pass model jointly reconstructs camera motion, scene geometry, hands (MANO), and objects, with object masks and 6DoF poses
- Trained on the automatically annotated large-scale EgoX-Data-6M dataset
- EgoX-Engine outputs meshes, depth, and hand parameters for world-grounded learning from human experience
More from Embodied
- Cyborg routine: checking free memory on a JavaCard implant with a reader and Python — TechPreacher · 2026-10-20
- First Humanoid Robot Fashion Challenge brings designers and robotics researchers together — kscottz · 2026-10-20
- Robotics feud: mjfit generates convex decompositions for MuJoCo, no simulator needed — KyleMorgenstein · 2026-10-20
- HoliWorld: scalable auto-labeling pipeline turns egocentric video into 3D/4D data — liuziwei7 · 2026-10-20
- mjfit peg benchmark under fire: cylinder-peg setup embeds a strong prior — YouJiacheng · 2026-10-20
- "Not jammed" isn't the metric: mjfit author clarifies benchmark measures contact onset and play — YouJiacheng · 2026-10-20