Research map / Image generation / Image restoration
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
Lanqing Guo, Chong Wang, Wenhan Yang, Siyu Huang, Yufei Wang, Hanspeter Pfister, Bihan Wen
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 ShadowDiffusion's degradation-aware unrolling to DMDM (ablation) | DMDM · ISTD | PSNR: 32.12 -> 32.33 | Improved |
| Add ShadowDiffusion's degradation-aware unrolling to DMDM (ablation) | DMDM · ISTD+ | PSNR: 35.21 -> 35.72 | Improved |
| Add ShadowDiffusion's degradation-aware unrolling to DMDM (ablation) | DMDM · SRD | PSNR: 34.36 -> 34.73 | Improved |
| Add iterative mask refinement (ablation) | ShadowDiffusion with Detector1 mask · SRD | PSNR: 34.55 -> 34.73 | Improved |
| Add iterative mask refinement (ablation) | ShadowDiffusion with Detector2 mask · SRD | PSNR: 33.61 -> 34.27 | Improved |
| Use ShadowDiffusion instead of BMNet | Shadow removal · SRD | PSNR (ALL): 31.69 -> 34.73 | Improved |
| Use ShadowDiffusion instead of BMNet | Shadow removal · ISTD | PSNR (ALL): 30.28 -> 32.33 | Improved |
| Use ShadowDiffusion instead of SP+M-Net | Shadow removal · ISTD+ | PSNR (All): 32.94 -> 35.72 | Improved |
| Use ShadowDiffusion instead of SR3 | Diffusion-based shadow removal · SRD | PSNR (ALL): 31.29 -> 34.73 | Improved |
Later papers that compared with this method
7 later accepted papers report ShadowDiffusion as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Image Restoration via Multi-Domain Learning (TPAMI 2026 · better on 1 of 1 shared result)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · better on 6 of 6 shared results)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · better on 3 of 3 shared results)
- Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal (ICCV 2025 · better on 3 of 3 shared results)
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal (CVPR 2025 · better on 0 of 2 shared results)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · better on 0 of 1 shared result)
- Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving (CVPR 2024 · better on 1 of 3 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
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.92)
- Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal (ICCV 2023 · similarity 0.91)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.91)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.88)
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal (CVPR 2025 · similarity 0.87)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 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.
