Open-source system reconstructs full 3D scenes from live video
bigaiguy · x · 2026-07-20
A new open-source system can reconstruct a full 3D scene from a single ordinary camera while the video is still running.
According to the post, it needs no LiDAR, depth sensor, or studio setup, and can run at around 20 FPS. The key claim is not just producing one good 3D frame, but staying stable across 10,000+ frames without drifting or collapsing. It is said to work on drone footage, driving videos, indoor walkthroughs, and large outdoor scenes, and to outperform slower optimization-based baselines on standard benchmarks.
Related event: SLAM3R: Real-Time 3D Scene Reconstruction from Monocular Video(4 posts)→
More from Research
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Finch 1: a geospatial foundation model trained on imagery from 50+ sensors — Scobleizer · 2026-10-27
- Skyfall AI's SKY-001 world model turns sketches into CAD builds in 3.9s, vs 199s for GPT-6 Astra — rohanpaul_ai · 2026-10-27
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27
- Researcher flags unresolved data transparency issues in compositionality evals — najoungkim · 2026-10-27
- Separate Forms from Estimators: Why Steer by Difference of Means When You Can Use SGD? — johnhewtt · 2026-10-27