AI Paper Atlas

Research map / Detection and segmentation / CNN features

Direction-Aware Spatial Context Features for Shadow Detection and Removal

Xiaowei Hu, Chi‐Wing Fu, Lei Zhu, Jing Qin, Pheng‐Ann Heng

TPAMI 2019 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 248 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 spatial context (without direction-aware attention) to the basic network (ablation)basic network · SBU shadow detectionBER: 6.55 -> 6.23Improved
add direction-aware attention weights to the spatial context (ablation)basic+context · SBU shadow detectionBER: 6.23 -> 5.59Improved
use two rounds of recurrent translation instead of one (ablation)DSC · SBU shadow detectionBER: 5.85 -> 5.59Improved
use three rounds instead of two with shared attention weights (ablation)DSC · SBU shadow detectionBER: 5.59 -> 5.85Hurt
share attention weights across rounds instead of separate copies (two rounds) (ablation)DSC · SBU shadow detectionBER: 6.02 -> 5.59Improved
replace VGG with ResNet-101 feature extractor (ablation)DSC · SBU shadow detectionBER: 5.59 -> 5.73No clear effect
add CRF post-processing (ablation)DSC · SBU shadow detectionBER: 5.68 -> 5.59Improved
train with color-adjusted shadow-free images (DSC+) and evaluate on adjusted ground truth (ablation)DSC · ISTD shadow removalRMSE: 8.54 -> 4.90Improved
train with color-adjusted shadow-free images (DSC+) and evaluate on adjusted ground truth (ablation)DSC · SRD shadow removalRMSE: 6.66 -> 6.12Improved
add color compensation, measured on non-shadow regions of ISTD against input (ablation)DSC · ISTD shadow removalRMSE: 7.07 -> 3.36Improved
use RGB instead of LAB color space (ablation)DSC · SRD shadow removalRMSE: 6.21 -> 6.05Mixed

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