Research map / 3D vision / Gaussian splatting
MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
Minh-Quan Viet Bui, Jongmin Park, Juan Luis Gonzalez, Jaeho Moon, Jihyong Oh, Munchurl Kim
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 deblurring module (BLCE) to SplineGS (ablation) | SplineGS · Stereo Blur full image | LPIPS: 0.141 -> 0.050 | Improved |
| Add blur-score guidance to the Neural ODE (ablation) | latent camera estimation · Stereo Blur full image | LPIPS: 0.057 -> 0.050 | Improved |
| Add blur-score guidance versus spline interpolation (ablation) | latent camera estimation · Stereo Blur full image | LPIPS: 0.058 -> 0.050 | Improved |
| Use LCEE exposure estimate instead of fixed T=0.5 (ablation) | MoBGS · Stereo Blur dynamic region | LPIPS: 0.117 -> 0.096 | Improved |
| Use LCEE instead of unconstrained learnable exposure (ablation) | MoBGS · Stereo Blur dynamic region | LPIPS: 0.128 -> 0.096 | Improved |
| Use fixed exposure T=0.9 (ablation) | MoBGS · Stereo Blur dynamic region | LPIPS: 0.096 -> 0.157 | Hurt |
| Use fixed exposure T=0.0 instead of LCEE (ablation) | MoBGS · Stereo Blur dynamic region | PSNR: 23.41 -> 23.20 | Hurt |
| Use MoBGS instead of MoBluRF | MoBGS · Stereo Blur full image | LPIPS: 0.078 -> 0.050 | Improved |
| Use MoBGS instead of cascade GShiftNet + SplineGS | MoBGS · Stereo Blur full image | PSNR: 26.54 -> 28.80 | Improved |
| Apply 2D deblurring preprocessing before SplineGS | SplineGS · Stereo Blur full image | LPIPS: 0.141 -> 0.074 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- SplineGS — SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025) · better on 6 of 6 shared results
- MoBluRF — MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video (TPAMI 2025) · better on 6 of 6 shared results
- Deblur4DGS — Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video (AAAI 2026) · better on 1 of 1 shared result
- DyBluRF — DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (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
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.91)
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.90)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.90)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.89)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.88)
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.
