Research map / Detection and segmentation / CNN features
Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
Wenda Zhao, Fan Zhao, Dong Wang, Huchuan Lu
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 BTBNet instead of a VGG16 fully convolutional network (ablation) | DBD network · Shi’s dataset | F-measure: 0.797 -> 0.853 | Improved |
| Use BTBNet instead of a VGG16 fully convolutional network (ablation) | DBD network · Our dataset | F-measure: 0.643 -> 0.730 | Improved |
| Add multi-scale streams and FNet, using two or three streams rather than one (ablation) | BTBNet · Shi’s dataset | F-measure: 0.853 -> 0.854 | Improved |
| Add multi-scale streams and FNet, using two or three streams rather than one (ablation) | BTBNet · Our dataset | F-measure: 0.730 -> 0.732 | Improved |
| Use three streams instead of two (ablation) | BTBNet+FNet · Shi’s dataset | F-measure: 0.853 -> 0.854 | Improved |
| Use three streams instead of two (ablation) | BTBNet+FNet · Our dataset | F-measure: 0.731 -> 0.732 | Improved |
| Add a fourth stream at scale 0.4 instead of using three streams (ablation) | BTBNet+FNet · Shi’s dataset | F-measure: 0.854 -> 0.853 | Hurt |
| Add a fourth stream at scale 0.4 instead of using three streams (ablation) | BTBNet+FNet · Our dataset | F-measure: 0.732 -> 0.731 | Hurt |
| Add RRNet recurrent reconstruction (ablation) | BTBNet(3S)+FNet · Shi’s dataset | F-measure: 0.854 -> 0.867 | Improved |
| Add RRNet recurrent reconstruction (ablation) | BTBNet(3S)+FNet · Our dataset | F-measure: 0.732 -> 0.761 | Improved |
| Add RRNet recurrent reconstruction (ablation) | BTBNet(3S)+FNet · Shi’s dataset | MAE: 0.130 -> 0.107 | Improved |
| Add RRNet recurrent reconstruction (ablation) | BTBNet(3S)+FNet · Our dataset | MAE: 0.230 -> 0.194 | Improved |
Closest papers by meaning
- Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Network (TPAMI 2019 · similarity 0.98)
- DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features (CVPR 2019 · similarity 0.94)
- Defocus Blur Detection via Depth Distillation (ECCV 2020 · similarity 0.94)
- 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 0.87)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · 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.
