Meta and CMU unveil TrackEverything: 3D point tracking across 1000+ frame videos
AdamWHarley · x · 2026-09-26
Meta and CMU Robotics introduce TrackEverything, a 3D point tracker that tracks all points across all frames of long videos (1000+ frames), built by Ayush Jain during a Meta internship.
- Key idea: tie computation to unique 3D scene content rather than redundant 2D pixels, using depth and camera pose to track the world in a stable coordinate system.
- It is especially effective for egocentric capture setups like Meta's Project Aria glasses.
- Code and project page are available (linked in the original post).
Related event: CMU and Meta Release TrackEverything for Long-Video 3D Point Tracking(2 posts)→
More from Embodied
- Why robots are humanoid: the models are trained on humans doing the work — floguo · 2026-09-26
- Trader on AI capex: finance people slow to catch Kimi/GLM coding-agent signals; robotics still pre-PMF — menhguin · 2026-09-26
- Musk: Human bandwidth is ~100 bits/sec, and Neuralink aims to close the gap with terabit AI — XFreeze · 2026-09-26
- AprilTag spotted at a Walmart in NY turns out to guide BrainCorp's autonomous floor scrubbers — carlosdponx · 2026-09-26
- Trader: Tesla is basically the only publicly traded mass-market robotics deployment play — menhguin · 2026-09-26
- Bolei Zhou to present long-horizon sidewalk navigation work at IROS 2026 — zhoubolei · 2026-09-26