AI Paper Atlas

Research map / Image generation / Image restoration

Bijective Mapping Network for Shadow Removal

Yurui Zhu, Jie Huang, Xueyang Fu, Feng Zhao, Qibin Sun, Zheng-Jun Zha

CVPR 2022 · Image generation › Image restoration · approach: Dehazing and deraining · 106 citations (OpenAlex)

Check 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
couple shadow removal and generation through shared, invertible mappings (ablation)BMNet · ISTD test, ALLRMSE: 5.33 -> 5.02Improved
add multi-scale color and mask guidance (ablation)BMNet · ISTD test, ALLRMSE: 5.17 -> 5.02Improved
add shadow-invariant color guidance (ablation)BMNet · ISTD test, ALLRMSE: 5.16 -> 5.02Improved
use SFT rather than concatenation for conditional feature modulation (ablation)BMNet SICGM · ISTD test, ALLRMSE: 5.16 -> 5.02Improved
increase invertible blocks from 4 to 5 (ablation)BMNet · ISTD test, ALLPSNR: 30.28 (+0.08)Improved
increase invertible blocks from 4 to 6 (ablation)BMNet · ISTD test, ALLRMSE: 5.02 -> 4.78Improved
use detected rather than ground-truth shadow masks (ablation)BMNet · ISTD+ test, ALLRMSE: 3.0 -> 3.5Hurt

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