Research map / Image generation / Image restoration
CRRN: Multi-Scale Guided Concurrent Reflection Removal Network
Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot
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 concurrent gradient and image inference with multi-scale gradient guidance | CRRN · SIR2 wild | SSIM: 0.884 -> 0.895 | Improved |
| Use concurrent gradient and image inference with multi-scale gradient guidance | CRRN · SIR2 wild | SI: 0.920 -> 0.925 | Improved |
| Use concurrent gradient and image inference with multi-scale gradient guidance | CRRN · SIR2 wild | SSIMr: 0.850 -> 0.861 | Improved |
| Use concurrent gradient and image inference with multi-scale gradient guidance | CRRN · SIR2 wild | SIr: 0.881 -> 0.890 | Improved |
| Add perceptually motivated SSIM/SI losses instead of using L1 loss only (ablation) | CRRN · SIR2 wild | SSIM: 0.883 -> 0.895 | Improved |
| Add perceptually motivated SSIM/SI losses instead of using L1 loss only (ablation) | CRRN · SIR2 wild | SIr: 0.865 -> 0.890 | Improved |
| Add GiN and gradient-feature guidance to IiN (ablation) | CRRN · SIR2 wild | SSIM: 0.867 -> 0.895 | Improved |
| Add GiN and gradient-feature guidance to IiN (ablation) | CRRN · SIR2 wild | SI: 0.892 -> 0.925 | Improved |
| Add GiN and gradient-feature guidance to IiN (ablation) | CRRN · SIR2 wild | SSIMr: 0.843 -> 0.861 | Improved |
| Add GiN and gradient-feature guidance to IiN (ablation) | CRRN · SIR2 wild | SIr: 0.859 -> 0.890 | Improved |
Later papers that compared with this method
1 later accepted paper reports CRRN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Face Image Reflection Removal (IJCV 2020 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CoRRN: Cooperative Reflection Removal Network (TPAMI 2019 · similarity 0.91)
- Single Image Reflection Removal Beyond Linearity (CVPR 2019 · similarity 0.89)
- Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements (CVPR 2019 · similarity 0.88)
- Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal (ECCV 2018 · similarity 0.88)
- Revisiting Single Image Reflection Removal In the Wild (CVPR 2024 · similarity 0.86)
- FIRM: Flexible Interactive Reflection ReMoval (AAAI 2025 · similarity 0.85)
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.
