Research map / Image generation / Image restoration
Blind Image Deconvolution Using Variational Deep Image Prior
Dong Huo, Abbas Masoumzadeh, Rafsanjany Kushol, Yee‐Hong Yang
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 |
|---|---|---|---|
| use variational Bayes with non-zero S(Is) instead of MAP, with extreme-channel prior (ablation) | DIP-Extreme · Lai et al. synthetic | PSNR: 22.39 -> 24.14 | Improved |
| use variational Bayes with non-zero S(Is) instead of MAP, with sparse prior (ablation) | DIP-Sparse · Lai et al. synthetic | PSNR: 20.53 -> 25.12 | Improved |
| use variational Bayes with non-zero S(Is) instead of MAP, with sparse prior (ablation) | DIP-Sparse · Lai et al. synthetic | SSIM: 0.659 -> 0.869 | Improved |
| add non-zero S(Is) without additive priors (ablation) | DIP · Lai et al. synthetic | PSNR: 20.67 -> 20.87 | No clear effect |
| add sparse image prior to DIP under MAP (ablation) | DIP · Lai et al. synthetic | PSNR: 20.67 -> 20.53 | Hurt |
| add extreme channel prior to DIP under MAP (ablation) | DIP · Lai et al. synthetic | PSNR: 20.67 -> 22.39 | Improved |
| add sparse prior with variational Bayes (VDIP-Sparse vs VDIP-Std) (ablation) | VDIP · Lai et al. synthetic | PSNR: 20.87 -> 25.12 | Improved |
| use VDIP-Sparse instead of VDIP-Extreme (sparse vs extreme-channel prior) (ablation) | VDIP · Lai et al. synthetic | PSNR: 24.14 -> 25.12 | Improved |
| use variational Bayes instead of MAP, sparse prior (ablation) | DIP-Sparse · Lai et al. synthetic | kernel recovery error: 0.00144 -> 0.00092 | Improved |
| use variational Bayes instead of MAP, extreme prior (ablation) | DIP-Extreme · Lai et al. synthetic | kernel recovery error: 0.00113 -> 0.00102 | Improved |
| use variational Bayes instead of MAP, sparse prior (ablation) | DIP-Sparse · Lai et al. real blurred | PIQE: 54.9295 -> 34.3614 | Improved |
| use variational Bayes instead of MAP, sparse prior (ablation) | DIP-Sparse · Lai et al. real blurred | NIQE: 7.9063 -> 3.8882 | Improved |
Closest papers by meaning
- Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding (ECCV 2024 · similarity 0.92)
- Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS 2019 · similarity 0.90)
- Neural Blind Deconvolution Using Deep Priors (CVPR 2020 · similarity 0.90)
- Deep Variational Network Toward Blind Image Restoration (TPAMI 2024 · similarity 0.90)
- Learning a Discriminative Prior for Blind Image Deblurring (CVPR 2018 · similarity 0.90)
- Image Reconstruction Via Autoencoding Sequential Deep Image Prior (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.
