Triangle Splatting SLAM: Imperial College's ECCV 2026 dense RGB-D SLAM with on-the-fly mesh extraction
rsasaki0109 · x · 2026-09-30
- Imperial College London (Nicholas Fry, Eric Dexheimer, Kirill Mazur, Paul Kelly, Andrew Davison) released Triangle Splatting SLAM, accepted to ECCV 2026: a dense RGB-D SLAM system using differentiable triangles as the 3D map representation for on-the-fly mesh extraction.
- The system tracks and maps with a differentiable triangle rasteriser: triangles are spawned from back-projected depth maps, optimised photometrically, and converted to a connected mesh on demand via Delaunay—unlike TSDF Fusion, tracking and editing share one unified representation.
- Demos include photorealistic rendering, physics simulation, thin structures, deformations, and online mesh editing; code and video are open-sourced.
More from Embodied
- Open-source self-driving guide adds VFH: binning LiDAR into 5° obstacle histograms — 4310sy · 2026-09-30
- Autonomous shipping startup Eight Knot raises ¥450M Series A to commercialize AI Captain — 4310sy · 2026-09-30
- DevDay stayed silent on OpenAI's Jony Ive hardware device, reportedly due 2027 — kimmonismus · 2026-09-30
- Manifold opens early access: robotics eval platform runs thousands of GPU-parallel rollouts in 30 mins — paigeinsf · 2026-09-30
- Giving Claude a Jetson Thor with dual stereo cameras to see what it builds — AIFlow_ML · 2026-09-30
- AnyStep-WAM Cuts Denoising Steps by Up to 85% in World Action Models Without Losing Success Rate — Rui Wang · 2026-09-30