Research map / 3D vision / Gaussian splatting
BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting
Lingzhe Zhao, Peng Wang, Peidong Liu
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 |
|---|---|---|---|
| increase number of virtual camera poses n from 3 to 10 (ablation) | BAD-Gaussians · Tanabata (severe blur) | PSNR: 25.43 -> 32.12 | Improved |
| increase n beyond 10 on a minor-blur scene (ablation) | BAD-Gaussians · Cozy2room | PSNR: 34.68 -> 34.63 (n=10 to 20) | No clear effect |
| use cubic B-spline instead of linear trajectory (ablation) | BAD-Gaussians · Deblur-NeRF real scenes | PSNR: 24.77 -> 26.11 | Improved |
| use cubic B-spline instead of linear trajectory (ablation) | BAD-Gaussians · Deblur-NeRF synthetic | PSNR: 33.92 -> 33.24 | Hurt |
| train Deblur-NeRF and DP-NeRF with ground-truth poses instead of COLMAP poses (ablation) | DP-NeRF · Deblur-NeRF synthetic, Cozyroom | PSNR: 29.02 -> 30.77 | Improved |
| jointly optimize exposure-time camera trajectory with Gaussians using physical blur model, versus implicit BAD-NeRF | BAD-Gaussians · Deblur-NeRF synthetic (deblurring) | PSNR: 3.6 dB higher than second best on average | Improved |
| Gaussian representation versus NeRF for sky regions | BAD-Gaussians · Deblur-NeRF synthetic, Factory | PSNR: 31.88 vs 32.18 (BAD-NeRF) | Hurt |
| plain 3D-GS or NeRF trained directly on blurred images | 3D-GS · Deblur-NeRF synthetic, Tanabata | PSNR: 20.51 vs 32.12 (BAD-Gaussians) | Hurt |
Later papers that compared with this method
2 later accepted papers report BAD-Gaussians* as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur (ECCV 2026 · better on 4 of 5 shared results)
- CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images (ICCV 2025 · better on 3 of 3 shared results)
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.
- BAD-NeRF — BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields (CVPR 2023) · better on 5 of 7 shared results
- DP-NeRF — DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors (CVPR 2023) · 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
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.91)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.91)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.90)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.90)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.90)
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.90)
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.
