Pith. sign in

REVIEW 5 cited by

vMAP: Vectorised Object Mapping for Neural Field SLAM

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.01838 v2 pith:HLTA2M6E submitted 2023-02-03 cs.CV

Xin Kong , Shikun Liu , Marwan Taher , Andrew J. Davison This is my paper · ORCID
classification cs.CV
keywords vmapobjectfieldneuralslamefficientobject-levelprior
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Floating Radiance Networks

    cs.CV 2026-08 conditional novelty 6.0 of 10

    FlaRe combines per-primitive latent radiance descriptors on planar Gaussians with a shared decoder and hardware ray tracing, making rendering, secondary rays, editing, and mesh extraction work in one scene model.

  2. Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data

    cs.RO 2025-06 conditional novelty 6.0 of 10

    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.

  3. VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new RGBD SLAM representation ties Gaussian positions to depth pixels, leaving only color, radius, and opacity learnable, enabling local-only optimization and higher rendering quality on several benchmarks.

  4. Query Quantized Neural SLAM

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Quantizing neural SLAM queries into discrete codes speeds up per-frame overfitting and improves reconstruction completion and tracking accuracy on RGB-D benchmarks.

  5. Is Semantic SLAM Ready for Embedded Systems ? A Comparative Survey

    cs.RO 2025-05 conditional novelty 3.0 of 10

    A comparative survey and embedded benchmark concluding that semantic geometric SLAM is more practical for real-time deployment than NeRF- or Gaussian-splatting-based semantic SLAM.

Pith tools