Research map / 3D vision / NeRF and radiance fields
MHED-SLAM: Multi-Scale Hybrid Encoding-Based Decoupled SLAM
Dengfang Feng, Wenyang Qin, Zhongchen Shi, Wei Chen, Yanhui Duan, Liang Xie, Erwei Yin
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 hybrid tri-plane+grid encoding instead of single hash grid (ablation) | MHED-SLAM · Replica room1 | Accuracy (cm): 4.06 -> 2.67 | Improved |
| use hybrid encoding instead of hash tri-plane only (ablation) | MHED-SLAM · Replica room1 | parameters (M): 1.79 -> 0.82 | Improved |
| hybrid encoding vs hash tri-plane on accuracy (ablation) | MHED-SLAM · Replica room1 | Accuracy (cm): 2.66 -> 2.67 | No clear effect |
| decouple reconstruction and rendering (no SKL) (ablation) | MHED-SLAM · Replica room1 | Depth L1 (cm): 0.94 -> 0.85 | Improved |
| add SKL loss lambda_S=5e-4 (ablation) | MHED-SLAM · Replica room1 | Depth L1 (cm): 0.85 -> 0.69 | Improved |
| increase SKL weight to 5e-3 (ablation) | MHED-SLAM · Replica room1 | Depth L1 (cm): 0.69 -> 0.73 | Hurt |
| MHED-SLAM vs QQ-SLAM on tracking | MHED-SLAM · Replica | ATE RMSE (cm): 0.91 -> 0.66 | Improved |
| MHED-SLAM vs MonoGS/QQ-SLAM on TUM RGB-D | MHED-SLAM · TUM RGB-D | ATE RMSE (cm): fr1/desk 2.61 -> 2.57; fr2/xyz 1.70 -> 1.91 | Mixed |
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.
- Co-SLAM — Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM (CVPR 2023) · better on 6 of 6 shared results
- SplaTAM — SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024) · better on 1 of 1 shared result
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
- MBA-SLAM: Motion Blur Aware Dense Visual SLAM With Radiance Fields Representation (TPAMI 2025 · similarity 0.87)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.87)
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM (CVPR 2024 · similarity 0.87)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.86)
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.86)
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (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.
