Research map / Image generation / Editing and style transfer
Face Image Reflection Removal
Renjie Wan, Boxin Shi, Haoliang Li, Ling‐Yu Duan, Alex Chichung 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 |
|---|---|---|---|
| add guided second image branch beyond SEN-only single-branch (ablation) | reflection removal network · Face reflection removal evaluation set | identity error: 0.592 -> 0.562 | Improved |
| add adversarial and local context losses (ablation) | reflection removal network · Face reflection removal evaluation set | identity error: 0.611 -> 0.562 | Improved |
| add identity loss in local refinement network (ablation) | reflection removal network · Face reflection removal evaluation set | identity error: 0.598 -> 0.562 | Improved |
| add prior embedding in local refinement network (ablation) | reflection removal network · Face reflection removal evaluation set | identity error: 0.606 -> 0.562 | Improved |
| use proposed method instead of ZN18 for face recognition Top-1 | reflection removal then recognition · Face recognition Top-1 | accuracy (%): 50.00% -> 53.41% | Improved |
| use proposed method instead of ZN18 for Top-10 | reflection removal then recognition · Face recognition Top-10 | accuracy (%): 80.68% -> 85.23% | Improved |
| apply non-learning reflection removal (NR17) before recognition | NR17 · Face recognition Top-1 | accuracy (%): 7.95% -> 1.14% | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CRRN — CRRN: Multi-Scale Guided Concurrent Reflection Removal Network (CVPR 2018) · 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
- Anti-Glare: Tightly Constrained Optimization for Eyeglass Reflection Removal (CVPR 2017 · similarity 0.89)
- Single Image Reflection Removal Beyond Linearity (CVPR 2019 · similarity 0.87)
- Benchmarking Single-Image Reflection Removal Algorithms (ICCV 2017 · similarity 0.86)
- Zero-Shot Learning for Reflection Removal of Single 360-Degree Image (ECCV 2022 · similarity 0.86)
- FIRM: Flexible Interactive Reflection ReMoval (AAAI 2025 · similarity 0.85)
- FaceMe: Robust Blind Face Restoration with Personal Identification (AAAI 2025 · similarity 0.84)
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.
