Research map / 3D vision / Depth and stereo
Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
Qi Zhang, Denis Rozumny, Francesco Girlanda, Sezer Karaoglu, Marc Pollefeys, Theo Gevers, Martin R. Oswald
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 fallback sub-frame blur modeling (ablation) | Unblur-SLAM · ReplicaBlurry severe blur | PSNR: 29.38 -> 29.94 | Improved |
| add Gaussian-based refinement after feed-forward deblurring (ablation) | Unblur-SLAM · Deblur-NeRF | PSNR: 28.22 -> 29.49 | Improved |
| add Gaussian-based refinement after feed-forward deblurring (ablation) | Unblur-SLAM · Deblur-NeRF | LPIPS: 0.1053 -> 0.0728 | Improved |
| add Gaussian-based refinement (ablation) | Unblur-SLAM · TUM runtime | FPS: 0.85 -> 0.74 | Hurt |
| add blur-score threshold to skip refinement for sharp frames (ablation) | Unblur-SLAM · TUM (3 sequences) | PSNR: 27.18 -> 29.46 | Improved |
| add blur-score threshold to skip refinement for sharp frames (ablation) | Unblur-SLAM · TUM (3 sequences) | FPS: 0.41 -> 0.74 | Improved |
| train deblurrer on DPDD instead of RealBlur_J (ablation) | Unblur-SLAM deblurrer · TUM | ATE RMSE: 0.400 -> 0.336 | Improved |
| train deblurrer on five ReplicaBlurry sequences instead of one (ablation) | Unblur-SLAM deblurrer · TUM | ATE RMSE: 0.352 -> 0.336 | Improved |
| train deblurrer on five ReplicaBlurry sequences instead of one (ablation) | Unblur-SLAM deblurrer · MCD | ATE RMSE: 0.155 -> 0.128 | Improved |
| add physics-constrained deblurring network to Droid-SLAM (ablation) | Droid-SLAM · TUM | ATE RMSE: 0.380 -> 0.336 | Improved |
| add physics-constrained deblurring network to Droid-SLAM (ablation) | Droid-SLAM · MCD | ATE RMSE: 0.138 -> 0.128 | Improved |
| train deblurrer on RealBlur_J instead of DPDD (ablation) | Droid-SLAM + deblurrer · MCD | ATE RMSE: 0.138 -> 0.139 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 7 of 7 on most shared results.
- CoMoGaussian — CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images (ICCV 2025) · better on 3 of 3 shared results
- I2-SLAM — I2-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM (ECCV 2024) · better on 3 of 3 shared results
- Droid-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 2 of 2 shared results
- DOF-GS — DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal (CVPR 2025) · better on 1 of 1 shared result
- BAGS — BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling (ECCV 2024) · better on 1 of 1 shared result
- DP-NeRF — DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors (CVPR 2023) · better on 1 of 1 shared result
- Deblur-NeRF — Deblur-NeRF: Neural Radiance Fields From Blurry Images (CVPR 2022) · 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
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · similarity 0.88)
- SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos (CVPR 2025 · similarity 0.88)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 2025 · similarity 0.87)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.87)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.87)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · 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.
