Open-source pipeline turns phone video into a navigable 3D world
anselm · x · 2026-07-21
A fully open-source pipeline turns a regular phone video into a navigable 3D world.
- It combines Depth Anything 3, Depth-Anything CPP, and SLAM to estimate depth frame by frame, track camera motion, and reconstruct a full 3D scene.
- Runs locally on a home GPU, with no cloud processing, subscriptions, or LiDAR hardware.
- The result is not yet perfectly photorealistic, but it shows that high-quality 3D scanning is becoming much more accessible.
More from Infra
- Nebius says SlimSpec speeds speculative decoding 8–9% without shrinking the vocabulary — Arindam_1729 · 2026-07-21
- NVIDIA brings its Cosmos 3 Edge world model to Jetson for on-device robot control — liu_mingyu · 2026-07-21
- A silicon photonic reservoir chip compensates fiber distortion in real time at 28 Gbps — bravo_abad · 2026-07-21
- Chamath says open-sourcing Grok would push AI margins from models to infra and apps — Dan_Jeffries1 · 2026-07-21
- EU AI competitiveness is under pressure as firms double down on chips, ethics, and talent — nordicinst · 2026-07-21
- AI bottlenecks are shifting to memory, optics, yield control and power — thedealdirector · 2026-07-21