Research map / 3D vision / Gaussian splatting
DINO-SLAM: DINO-Informed RGB-D SLAM for Neural Implicit and Explicit Representations
ZIREN GONG, Xiaohan Li, Fabio Tosi, Youmin Zhang, Stefano Mattoccia, Jun Wu, Matteo Poggi
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 vanilla DINO features (ablation) | ESLAM · Replica | depth L1 (cm): 0.94 -> 0.79 | Improved |
| add geoDINO via SGE instead of vanilla DINO (ablation) | ESLAM · Replica | depth L1 (cm): 0.79 -> 0.63 | Improved |
| concatenate depth features to DINO instead of SGE (ablation) | ESLAM · Replica | depth L1 (cm): 0.79 -> 0.75 (vs geoDINO 0.63) | Improved |
| add vanilla DINO features (ablation) | GauS-SLAM · Replica | PSNR (dB): 40.25 -> 40.78 | Improved |
| add geoDINO via SGE instead of vanilla DINO (ablation) | GauS-SLAM · Replica | PSNR (dB): 40.78 -> 41.42 | Improved |
| add SGE/DINO to various SLAM encodings | Co-SLAM, ESLAM, SNI-SLAM, Point-SLAM, SplaTAM, MonoGS, GauS-SLAM · Replica | ATE RMSE (cm): e.g. ESLAM 0.63 -> 0.49; GauS-SLAM 0.06 -> 0.05 | Improved |
| add depth noise to input (ablation) | DINO-SLAM (GS) · Replica office1 | PSNR (dB): 44.65 -> 42.38 | Hurt |
| add geoDINO | GauS-SLAM · ScanNet | avg ATE RMSE (cm): 9.1 -> 7.3 | Improved |
| add geoDINO | ESLAM · TUM RGB-D | avg ATE RMSE (cm): 2.00 -> 1.93 | Improved |
| add geoDINO | ESLAM · Replica room0 speed | FPS: 4.62 -> 2.55 | Hurt |
| add geoDINO | GauS-SLAM · Replica room0 speed | FPS: 0.59 -> 0.58 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- ESLAM — ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields (CVPR 2023) · better on 7 of 7 shared results
- PLGSLAM — PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment (CVPR 2024) · better on 0 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
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D 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 0.86)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.85)
- DINO-Foresight: Looking into the Future with DINO (NeurIPS 2025 · similarity 0.85)
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · similarity 0.85)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (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.
