Research map / 3D vision / Depth and stereo
MapNet: An Allocentric Spatial Memory for Mapping Environments
João F. Henriques, Andrea Vedaldi
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 |
|---|---|---|---|
| use allocentric spatial-memory matching instead of direct pose prediction | MapNet on ResearchDoom · ResearchDoom | APE-50: 296 -> 197 | Improved |
| use allocentric spatial-memory matching instead of direct pose prediction | MapNet on ResearchDoom · ResearchDoom | APE-5: 19 -> 23 | Hurt |
| add concatenated preceding-frame input (ablation) | MapNet-32 on ResearchDoom · ResearchDoom | APE-5: 23 -> 20 | Improved |
| add concatenated preceding-frame input (ablation) | MapNet-32 on ResearchDoom · ResearchDoom | APE-50: 197 -> 219 | Hurt |
| add concatenated preceding-frame input (ablation) | MapNet-32 on ResearchDoom · ResearchDoom | ATE-50: 74 -> 73 | Improved |
| add concatenated preceding-frame input (ablation) | MapNet on Active Vision Dataset · Active Vision Dataset | APE-5: 222 -> 207 | Improved |
| add concatenated preceding-frame input (ablation) | MapNet on Active Vision Dataset · Active Vision Dataset | APE-50: 1844 -> 1338 | Improved |
| add concatenated preceding-frame input (ablation) | MapNet on Active Vision Dataset · Active Vision Dataset | ATE-50: 614 -> 464 | Improved |
| use allocentric spatial-memory matching instead of direct pose prediction | MapNet on Active Vision Dataset · Active Vision Dataset | APE-50: 1860 -> 1844 | Improved |
Later papers that compared with this method
9 later accepted papers report MapNet as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- DFNet: Enhance Absolute Pose Regression with Direct Feature Matching (ECCV 2022 · better on 2 of 2 shared results)
- GTCaR: Graph Transformer for Camera Re-Localization (ECCV 2022 · better on 2 of 2 shared results)
- Camera Pose Auto-Encoders for Improving Pose Regression (ECCV 2022 · better on 1 of 1 shared result)
- PoGO-Net: Pose Graph Optimization With Graph Neural Networks (ICCV 2021 · better on 2 of 2 shared results)
- Learning Multi-Scene Absolute Pose Regression With Transformers (ICCV 2021 · better on 2 of 2 shared results)
- AtLoc: Attention Guided Camera Localization (AAAI 2020 · better on 6 of 6 shared results)
- Local Supports Global: Deep Camera Relocalization With Sequence Enhancement (ICCV 2019 · better on 8 of 8 shared results)
- CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization (ICCV 2019 · better on 4 of 4 shared results)
1 more not listed.
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
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.86)
- Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction (ICLR 2024 · similarity 0.86)
- AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models (NeurIPS 2026 · similarity 0.86)
- Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences (NeurIPS 2024 · similarity 0.86)
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR 2024 · similarity 0.86)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · 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.
