Research map / Image generation / Image restoration
OID: Outlier Identifying and Discarding in Blind Image Deblurring
Liang Chen, Faming Fang, Jiawei Zhang, Jun Liu, Guixu Zhang
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 |
|---|---|---|---|
| re-identify outliers in both image and kernel updating steps with inner iterations instead of updating {I,K,W} once in sequence (ablation) | OID · Blurry image with impulsive noise (Fig. 5) | deblurring quality | Improved |
| add inner iteration of weights and latent variables to the proposed update (ablation) | OID · Blurry image with impulsive noise (Fig. 5) | deblurring quality | Improved |
| use OID outlier weighting instead of Pan et al. detection in the same MAP model (ablation) | OID · non-blind deblurring, increasing impulsive noise density | average PSNR | Improved |
| use OID outlier weighting instead of Cho et al. EM-based detection (ablation) | OID · non-blind deblurring, increasing impulsive noise density | average PSNR | Improved |
| OID vs Dong et al. on impulsive-noise blind deblurring | OID · Synthetic impulsive-noise set (120 images) | success rate at error ratio under 2: 47% -> 69% | Improved |
| apply OID to images without outliers | OID · benchmark dataset without outliers | average PSNR | No clear effect |
| replace l0 with l1 norm for sparse outlier constraint (ablation) | OID · OID model | computation | No clear effect |
Closest papers by meaning
- Blind Image Deblurring With Outlier Handling (ICCV 2017 · similarity 0.92)
- Robust Kernel Estimation With Outliers Handling for Image Deblurring (CVPR 2016 · similarity 0.92)
- Self-Paced Kernel Estimation for Robust Blind Image Deblurring (ICCV 2017 · similarity 0.90)
- Learning Data Terms for Non-blind Deblurring (ECCV 2018 · similarity 0.88)
- Noise-Blind Image Deblurring (CVPR 2017 · similarity 0.87)
- Blind Deblurring for Saturated Images (CVPR 2021 · 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.
