AI Paper Atlas

Research map / Detection and segmentation / CNN features

CANet: A Context-Aware Network for Shadow Removal

Zipei Chen, Chengjiang Long, Ling Zhang, Chunxia Xiao

ICCV 2021 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 114 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 learned contextual patch matching (CPM) instead of hand-crafted descriptor matching (ablation)CANet · ISTD whole imageRMSE (LAB): 6.98 -> 6.15Improved
add learned contextual patch matching (CPM) instead of hand-crafted descriptor matching (ablation)CANet · SRD whole imageRMSE (LAB): 6.89 -> 5.98Improved
add CPM instead of MatchNet for patch matching (ablation)CANet · ISTD whole imageRMSE (LAB): 6.52 -> 6.15Improved
add CPM instead of MatchNet for patch matching (ablation)CANet · SRD whole imageRMSE (LAB): 6.35 -> 5.98Improved
add contextual feature transfer (CFT) (ablation)CANet · ISTD whole imageRMSE (LAB): 7.54 -> 6.15Improved
add contextual feature transfer (CFT) (ablation)CANet · SRD whole imageRMSE (LAB): 6.96 -> 5.98Improved
add Gaussian sampling to feature transfer instead of direct replacement (ablation)CANet · ISTD whole imageRMSE (LAB): 6.56 -> 6.15Improved
add Gaussian sampling to feature transfer instead of direct replacement (ablation)CANet · SRD whole imageRMSE (LAB): 6.25 -> 5.98Improved
add context-aware Stage-I with CPM and CFT to one-stage DenseUNet (ablation)DenseUNet · ISTD whole imageRMSE (LAB): 7.58 -> 6.15Improved
add context-aware Stage-I with CPM and CFT to one-stage DenseUNet (ablation)DenseUNet · SRD whole imageRMSE (LAB): 7.28 -> 5.98Improved
add Gaussian sampling to feature transfer instead of direct replacement (ablation)CANet · ISTD shadow areaRMSE (LAB): 9.15 -> 8.86Improved
add CPM instead of MatchNet for patch matching (ablation)CANet · ISTD shadow areaRMSE (LAB): 9.16 -> 8.86Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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