Research map / Detection and segmentation / CNN features
DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 separate cross-layer shallow/deep feature fusion and refinement (ablation) | DeFusionNet · Shi et al.'s dataset | Fβ: 0.907 -> 0.917 | Helped |
| add separate cross-layer shallow/deep feature fusion and refinement (ablation) | DeFusionNet · DUT | Fβ: 0.904 -> 0.922 | Helped |
| add fusion of output maps from all layers (ablation) | DeFusionNet · Shi et al.'s dataset | Fβ: 0.911 -> 0.917 | Helped |
| add fusion of output maps from all layers (ablation) | DeFusionNet · DUT | Fβ: 0.915 -> 0.922 | Helped |
| increase recurrent refinement from 1 to 3 steps (ablation) | DeFusionNet · Shi et al.'s dataset | Fβ: 0.702 -> 0.917 | Helped |
| increase recurrent refinement from 1 to 3 steps (ablation) | DeFusionNet · DUT | Fβ: 0.756 -> 0.922 | Helped |
| increase recurrent refinement from 3 to 6 steps (ablation) | DeFusionNet · Shi et al.'s dataset | Fβ: 0.917 -> 0.919 | No clear effect |
| increase recurrent refinement from 3 to 6 steps (ablation) | DeFusionNet · DUT | Fβ: 0.922 -> 0.924 | No clear effect |
Closest papers by meaning
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.89)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · similarity 0.87)
- Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring (AAAI 2024 · similarity 0.87)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.87)
- LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network (CVPR 2024 · similarity 0.86)
- Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries (CVPR 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.