Research map / Image generation / Image restoration
A Unified Approach of Multi-Scale Deep and Hand-Crafted Features for Defocus Estimation
Jinsun Park, Yu-Wing Tai, Donghyeon Cho, In So Kweon
Check 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 |
|---|---|---|---|
| concatenate deep and hand-crafted features instead of using the deep feature alone (ablation) | Defocus feature classifier · 11-class defocus feature classification | accuracy (%): 89.38 -> 94.16 | Improved |
| use multi-scale patch extraction instead of single-scale extraction (ablation) | f_B defocus feature classifier · 11-class defocus feature classification | accuracy (%): 91.00% -> 94.16 | Improved |
| add the gradient feature to [f_D, f_S, f_C] (ablation) | Defocus feature classifier · 11-class defocus feature classification | accuracy (%): 93.25% -> 94.16 | Improved |
| add the DCT feature to [f_G, f_S, f_C] (ablation) | Defocus feature classifier · 11-class defocus feature classification | accuracy (%): 91.10% -> 94.16 | Improved |
| combine deep and hand-crafted features rather than use either feature family alone (ablation) | Defocus map estimation · Blur detection dataset | defocus map quality | Improved |
| propagate sparse estimates using an edge-preserving smoothed image rather than the color-line-model prior | Defocus map estimation · Blur detection dataset | segmentation quality | Improved |
| evaluate the proposed method instead of Shi et al.'s method | Defocus estimation · Shi et al. dataset | RelOrder: 0.1393 -> 0.1572 | Improved |
| add random classification seed points in large homogeneous regions (ablation) | Sparse defocus map propagation · Large homogeneous image regions | defocus accuracy | Improved |
Closest papers by meaning
- Deep Defocus Map Estimation Using Domain Adaptation (CVPR 2019 · similarity 0.91)
- Estimating Defocus Blur via Rank of Local Patches (ICCV 2017 · similarity 0.91)
- Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries (CVPR 2025 · similarity 0.87)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.87)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · similarity 0.87)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.86)
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.
