EgoXperience turns egocentric video into world-grounded 3D reconstructions in one forward pass
liuziwei7 · x · 2026-10-20
A team led by Ziwei Liu (NTU) introduces EgoXperience, a full-stack paradigm that converts egocentric video into world-grounded representations:
- EgoX-Engine transforms captured human experience into aligned supervision across RGB, depth, cameras, hands, object masks, 6DoF trajectories, meshes, and task captions.
- EgoX-Data-6M & EgoX-Bench provide 50 hours of video, 5.4M frames, and 270 tasks with a quality-controlled benchmark for joint reconstruction.
- EgoX extends the VGGT feed-forward paradigm from scenes to egocentric video, jointly reconstructing cameras, scenes, hands, and objects in a shared metric world frame with a single forward pass.
Paper and resources are available on Hugging Face (arXiv 2610.26625).
More from Embodied
- New "Embodied Olympics" Benchmark: GPT and Claude Agents Play Soccer and Ping Pong — ManlingLi_ · 2026-10-20
- SF founders go deep in Shenzhen's Huaqiangbei building BCIs and wearables — LoganGrasby · 2026-10-20
- MicroAGI trains a handyman model with tens of thousands of hours of video — isnit0 · 2026-10-20
- Uber-linked group secretly campaigns to ban robotaxis in Washington D.C. — gabriberton · 2026-10-20
- Meta admits smart glasses were recording conversations without the wake word — Resident-Fall4351 · 2026-10-20
- Wayve demos its Fiat 500e autonomous prototype on Turin's iconic Lingotto rooftop track — alexgkendall · 2026-10-20