Research map / Image generation / Image restoration
Location-Aware Single Image Reflection Removal
Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson W.H. Lau
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 RDM and TSM (ablation) | location-aware SIRR network · SIR2 | PSNR: 23.237 -> 24.117 | Improved |
| add LSTM recurrence (ablation) | location-aware SIRR network · SIR2 | PSNR: 23.808 -> 24.117 | Improved |
| add Laplacian-kernel multi-scale submodule (MLSM) instead of single-scale (ablation) | RDM · SIR2 | PSNR: 23.089 -> 24.117 | Improved |
| use learned Laplacian features instead of edge features (ablation) | RDM · SIR2 | PSNR: 23.612 -> 24.117 | Improved |
| add fine-tuning of Laplacian kernel parameters (ablation) | MLSM · SIR2 | PSNR: 23.640 -> 24.117 | Improved |
| Laplacian kernel initialization instead of random init (ablation) | RDM · SIR2 | SSIM: 0.893 -> 0.901 | Improved |
| Laplacian kernel initialization instead of random init (ablation) | RDM · Zhang et al. | PSNR: 21.784 -> 23.338 | Improved |
| add gradient clipping in MLSM (ablation) | RDM · SIR2 | PSNR: 23.901 -> 24.117 | Improved |
| add SSIM loss (ablation) | training loss · SIR2 | PSNR: 15.653 -> 24.117 | Improved |
| add perceptual loss (ablation) | training loss · SIR2 | PSNR: 22.725 -> 24.117 | Improved |
| add pixel loss (ablation) | training loss · SIR2 | PSNR: 23.365 -> 24.117 | Improved |
| add adversarial loss (ablation) | training loss · SIR2 | PSNR: 23.571 -> 24.117 | Improved |
Closest papers by meaning
- Revisiting Single Image Reflection Removal In the Wild (CVPR 2024 · similarity 0.89)
- LightRR: A Lightweight Network for Single Image Reflection Removal (CVPR 2026 · similarity 0.88)
- A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal (TPAMI 2025 · similarity 0.87)
- Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal (ECCV 2018 · similarity 0.87)
- RefMover: Diffusion-Based Single Image Reflection Removal With Language and Region Guidance (TPAMI 2026 · similarity 0.87)
- Reversible Decoupling Network for Single Image Reflection Removal (CVPR 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.
