LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal
Hong Yang, Gongrui Nan, Mingbao Lin, Fei Chao, Yunhang Shen, Ke Li,, Rongrong Ji

TL;DR
This paper introduces LAB-Net, a lightweight neural network that processes images in the LAB color space for efficient and effective shadow removal, outperforming existing methods while reducing model size and computational costs.
Contribution
The paper proposes a novel LAB-Net architecture with a two-branch structure and dilated convolutions, improving shadow removal performance and efficiency over prior models.
Findings
Outperforms state-of-the-art shadow removal methods.
Reduces model parameters and computational costs significantly.
Effective use of LAB color space and non-shadow region priors.
Abstract
This paper focuses on the limitations of current over-parameterized shadow removal models. We present a novel lightweight deep neural network that processes shadow images in the LAB color space. The proposed network termed "LAB-Net", is motivated by the following three observations: First, the LAB color space can well separate the luminance information and color properties. Second, sequentially-stacked convolutional layers fail to take full use of features from different receptive fields. Third, non-shadow regions are important prior knowledge to diminish the drastic color difference between shadow and non-shadow regions. Consequently, we design our LAB-Net by involving a two-branch structure: L and AB branches. Thus the shadow-related luminance information can well be processed in the L branch, while the color property is well retained in the AB branch. In addition, each branch is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Video Surveillance and Tracking Methods · Remote-Sensing Image Classification
MethodsMax Pooling · Dense Connections · Sigmoid Activation · Average Pooling
