A hybrid 3D Gaussian splatting plus explicit mesh representation, optimized end-to-end with differentiable rendering and physics, reconstructs objects and calibrates robot poses from imperfect real-world RGB trajectories.
vMAP: Vectorised Object Mapping for Neural Field SLAM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present vMAP, an object-level dense SLAM system using neural field representations. Each object is represented by a small MLP, enabling efficient, watertight object modelling without the need for 3D priors. As an RGB-D camera browses a scene with no prior information, vMAP detects object instances on-the-fly, and dynamically adds them to its map. Specifically, thanks to the power of vectorised training, vMAP can optimise as many as 50 individual objects in a single scene, with an extremely efficient training speed of 5Hz map update. We experimentally demonstrate significantly improved scene-level and object-level reconstruction quality compared to prior neural field SLAM systems. Project page: https://kxhit.github.io/vMAP.
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data
A hybrid 3D Gaussian splatting plus explicit mesh representation, optimized end-to-end with differentiable rendering and physics, reconstructs objects and calibrates robot poses from imperfect real-world RGB trajectories.