Triangle Splatting SLAM uses differentiable triangles for dense RGB-D mapping
janusch_patas · x · 2026-07-29
Triangle Splatting SLAM is a dense RGB-D SLAM system that represents the scene with differentiable triangles, enabling on-the-fly mesh extraction.
The method uses a differentiable triangle rasteriser for tracking and mapping: triangles are spawned from back-projected depth maps, optimised photometrically, and can be turned into a connected mesh when needed. The authors say this unifies tracking, editing, and mesh recovery in one representation, unlike TSDF-fusion-style pipelines.
The demo highlights photorealistic rendering, physics simulation, thin-structure handling, deformations, and online mesh editing/tracking. The code is out, and an experimental branch uses a rasteriser from another contributor, though densification is not fully implemented yet.
More from Research
- Microsoft removes Mage Flow and points to a more efficient Qwen-VL-class encoder — Dante_77A · 2026-07-29
- Profluentbio is building protein foundation models for AI-designed therapeutics — nathanbenaich · 2026-07-29
- VisualPatchWorld: Code World Models for Efficient Planning — HKBU-KnowComp · 2026-07-29
- A staged diagnosis finds most short-text generation loss comes from the codec — ITMO · 2026-07-29
- Nature paper measures non-Gaussian order-parameter statistics across a phase transition — burny_tech · 2026-07-29
- Quanta profiles 2026 Fields Medalist Yu Deng and his meticulous research style — burny_tech · 2026-07-29