Research map / 3D vision / NeRF and radiance fields
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
Mohammad Mahdi Johari, Camilla Carta, François Fleuret
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 ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · Replica | Depth L1 (cm): 3.29 ± 0.33 -> 1.18 ± 0.05 | Improved |
| Use ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · Replica | ATE Mean (cm): 1.56 ± 0.29 -> 0.52 ± 0.03 | Improved |
| Use ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · ScanNet | ATE Mean (cm): 9.3 ± 0.7 -> 6.5 ± 0.2 | Improved |
| Use ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · TUM RGB-D fr1/desk | ATE RMSE (cm): 2.85 -> 2.47 | Improved |
| Use ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · TUM RGB-D fr2/xyz | ATE RMSE (cm): 2.39 -> 1.11 | Improved |
| Use ESLAM instead of NICE-SLAM | Dense RGB-D SLAM · TUM RGB-D fr3/office | ATE RMSE (cm): 3.02 -> 2.42 | Improved |
| Replace voxel-grid features with axis-aligned feature planes and model geometry with TSDF | ESLAM · Replica room0 | Frame processing time (s): 2.10 -> 0.18 | Improved |
| Replace voxel-grid features with axis-aligned feature planes and model geometry with TSDF | ESLAM · ScanNet scene0000 | Frame processing time (s): 3.35 -> 0.55 | Improved |
Later papers that compared with this method
13 later accepted papers report ESLAM as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.
- DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations (ECCV 2026 · better on 7 of 7 shared results)
- UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception (ICML 2026 · better on 1 of 1 shared result)
- MBA-SLAM: Motion Blur Aware Dense Visual SLAM With Radiance Fields Representation (TPAMI 2025 · better on 2 of 2 shared results)
- DyGS-SLAM: Real-Time Accurate Localization and Gaussian Reconstruction for Dynamic Scenes (ICCV 2025 · better on 1 of 1 shared result)
- LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System (ECCV 2024 · better on 12 of 15 shared results)
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · better on 3 of 6 shared results)
- Implicit Event-RGBD Neural SLAM (CVPR 2024 · better on 5 of 6 shared results)
- PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment (CVPR 2024 · better on 6 of 6 shared results)
5 more not listed.
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 13 of 13 shared results
- iMAP* — iMAP: Implicit Mapping and Positioning in Real-Time (ICCV 2021) · better on 11 of 11 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
- PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment (CVPR 2024 · similarity 0.89)
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM (CVPR 2024 · similarity 0.89)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.87)
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · similarity 0.87)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.87)
- SNI-SLAM: Semantic Neural Implicit SLAM (CVPR 2024 · similarity 0.87)
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.
