Research map / 3D vision / 3D generation
vMAP: Vectorised Object Mapping for Neural Field SLAM
Xin Kong, Shikun Liu, Marwan Taher, Andrew J. Davison
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Represent scene instances as separate object MLPs rather than one scene-level field | vMAP · Replica (8-scene average) | Object completion [cm]: 2.38 -> 1.44 | Improved |
| Represent scene instances as separate object MLPs rather than one scene-level field | vMAP · Replica (8-scene average) | Scene completion [cm]: 2.88 -> 2.39 | Improved |
| Remove the background model (ablation) | vMAP · Replica Room-0 | Mapping time: 226ms -> 120ms | Improved |
| Use a shared MLP with per-object latent codes instead of separate stacked MLPs (ablation) | vMAP · Replica Room-0 | Object-level reconstruction quality | Hurt |
| Increase object MLP hidden size beyond 16 (ablation) | vMAP · Replica Room-0 | Object-level reconstruction quality | No clear effect |
| Train object MLPs with vectorised operations rather than sequential for-loops (ablation) | vMAP · Replica Room-0 | Training speed | Improved |
Later papers that compared with this method
2 later accepted papers report vMap* as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- O^2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model (AAAI 2024 · better on 4 of 4 shared results)
- Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors (NeurIPS 2023 · better on 0 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- NICE-SLAM* — NICE-SLAM: Neural Implicit Scalable Encoding for SLAM (CVPR 2022) · better on 6 of 7 shared results
- iMAP* — iMAP: Implicit Mapping and Positioning in Real-Time (ICCV 2021) · better on 6 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · similarity 0.88)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 2025 · similarity 0.87)
- DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors (AAAI 2024 · similarity 0.86)
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM (CVPR 2024 · similarity 0.86)
- Query Quantized Neural SLAM (AAAI 2025 · similarity 0.86)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
