Research map / Point clouds / Point cloud classification
EMPNet: Neural Localisation and Mapping Using Embedded Memory Points
Gil Avraham, Yan Zuo, Thanuja Dharmasiri, Tom Drummond
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 |
|---|---|---|---|
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · VIZDoom | APE-50: 168.3 -> 160.9 | Improved |
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · VIZDoom | APE-5: 10.10 -> 10.45 | Hurt |
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · VIZDoom | ATE-50: 68 -> 59 | Improved |
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · Active Vision Dataset | APE-5: 181.6 -> 171.8 | Improved |
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · Active Vision Dataset | APE-50: 1201 -> 1150 | Improved |
| add pose regularisation losses (EMP-Net-Pose) to EMP-Net | EMP-Net · Active Vision Dataset | ATE-50: 381 -> 360 | Improved |
| vary temperature tau between 10^3 and 10^6 (ablation) | EMP-Net · VIZDoom | localisation error | No clear effect |
| use learned embedding memory (EMP-Net) instead of standard point-to-point ICP under growing camera baseline | EMP-Net · VIZDoom | APE vs camera baseline | Improved |
Closest papers by meaning
- MapNet: An Allocentric Spatial Memory for Mapping Environments (CVPR 2018 · similarity 0.87)
- Point-SLAM: Dense Neural Point Cloud-based SLAM (ICCV 2023 · similarity 0.86)
- Geometry-Aware Learning of Maps for Camera Localization (CVPR 2018 · similarity 0.86)
- Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views (AAAI 2021 · similarity 0.86)
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR 2024 · similarity 0.84)
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.84)
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.
