AI Paper Atlas

Research map / Image generation / Image restoration

Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal

Lanqing Guo, Chong Wang, Wenhan Yang, Yufei Wang, Bihan Wen

ICCV 2023 · Image generation › Image restoration · approach: Dehazing and deraining · 32 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 iterative reflectance maintenance during sampling (ablation)BCDiff · ISTD (all image)PSNR: 26.01 -> 32.73Improved
add pretrained diffusion model sampling on top of intrinsic decomposition (ablation)BCDiff · ISTD (all image)SSIM: 0.952 -> 0.962Improved
train decomposition with simulated shadow image set (n=4) instead of n=1 (ablation)SIID model · ISTD (shadow region)PSNR: 35.16 -> 35.91Improved
add illumination-consistency constraint in sampling (ablation)BCDiff · ISTD (all image)PSNR: 32.40 -> 32.73Improved
use detected shadow masks instead of GT masksBCDiff · ISTD (all image)PSNR: 32.73 -> 32.11Hurt
unsupervised BCDiff vs supervised SP+M-NetBCDiff · ISTD (all image)PSNR: 32.73 vs 32.94Mixed
BCDiff vs prior unsupervised G2R on shadow regionBCDiff · ISTD (shadow region)PSNR: 33.58 -> 35.91Improved

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