Research map / Image generation / Image restoration
L-DiffER: Single Image Reflection Removal with Language-based Diffusion Model
Yuchen Hong, Haofeng Zhong, Shuchen Weng, Jinxiu S Liang, Boxin Shi
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 language-guided diffusion with iterative refinement and constraints vs best prior single-image method | reflection removal · Average (540) | PSNR: 24.79 -> 25.08 | Improved |
| L-DiffER on Nature dataset vs IBCLN on SSIM/PSNR | reflection removal · Nature (20) | PSNR: 23.69 -> 23.95 | Improved |
| add iterative condition refinement (color and structure) (ablation) | L-DiffER · Average (540) | FID: 60.12 -> 46.58 | Improved |
| add color condition refinement (ablation) | L-DiffER · Average (540) | PSNR: 24.42 -> 25.08 | Improved |
| add structure condition refinement (ablation) | L-DiffER · Average (540) | FID: 53.71 -> 46.58 | Improved |
| add saturation-aware structure constraint (ablation) | L-DiffER · Average (540) | PSNR: 24.16 -> 25.08 | Improved |
| add maximum value constraint (ablation) | L-DiffER · Average (540) | PSNR: 24.73 -> 25.08 | Improved |
| add both constraints together (ablation) | L-DiffER · Average (540) | FID: 63.68 -> 46.58 | Improved |
Later papers that compared with this method
1 later accepted paper reports L-DiffER as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- UniSER: A Foundation Model for Unified Soft Effects Removal (CVPR 2026 · better on 1 of 1 shared result)
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
- Restoration by Generation with Constrained Priors (CVPR 2024 · similarity 0.87)
- IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models (ICML 2025 · similarity 0.87)
- One-Step Effective Diffusion Network for Real-World Image Super-Resolution (NeurIPS 2024 · similarity 0.87)
- Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration (CVPR 2025 · similarity 0.87)
- Language-guided Image Reflection Separation (CVPR 2024 · similarity 0.86)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 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.
