AI Paper Atlas

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

CVPR 2023 · Image generation › Image restoration · approach: Dehazing and deraining · 130 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add ShadowDiffusion's degradation-aware unrolling to DMDM (ablation)DMDM · ISTDPSNR: 32.12 -> 32.33Improved
Add ShadowDiffusion's degradation-aware unrolling to DMDM (ablation)DMDM · ISTD+PSNR: 35.21 -> 35.72Improved
Add ShadowDiffusion's degradation-aware unrolling to DMDM (ablation)DMDM · SRDPSNR: 34.36 -> 34.73Improved
Add iterative mask refinement (ablation)ShadowDiffusion with Detector1 mask · SRDPSNR: 34.55 -> 34.73Improved
Add iterative mask refinement (ablation)ShadowDiffusion with Detector2 mask · SRDPSNR: 33.61 -> 34.27Improved
Use ShadowDiffusion instead of BMNetShadow removal · SRDPSNR (ALL): 31.69 -> 34.73Improved
Use ShadowDiffusion instead of BMNetShadow removal · ISTDPSNR (ALL): 30.28 -> 32.33Improved
Use ShadowDiffusion instead of SP+M-NetShadow removal · ISTD+PSNR (All): 32.94 -> 35.72Improved
Use ShadowDiffusion instead of SR3Diffusion-based shadow removal · SRDPSNR (ALL): 31.29 -> 34.73Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy