Progressive Recurrent Network for Shadow Removal
This addresses the unresolved problem of shadow removal in images, which is important for computer vision applications, but the approach is incremental as it builds on existing deep learning methods with a novel progressive design.
The paper tackles single-image shadow removal by proposing a Progressive Recurrent Network (PRNet) that removes shadows in a coarse-to-fine fashion, achieving superior performance on benchmarks like ISTD, ISTD+, and SRD while using only 29% of the parameters of the best published method.
Single-image shadow removal is a significant task that is still unresolved. Most existing deep learning-based approaches attempt to remove the shadow directly, which can not deal with the shadow well. To handle this issue, we consider removing the shadow in a coarse-to-fine fashion and propose a simple but effective Progressive Recurrent Network (PRNet). The network aims to remove the shadow progressively, enabing us to flexibly adjust the number of iterations to strike a balance between performance and time. Our network comprises two parts: shadow feature extraction and progressive shadow removal. Specifically, the first part is a shallow ResNet which constructs the representations of the input shadow image on its original size, preventing the loss of high-frequency details caused by the downsampling operation. The second part has two critical components: the re-integration module and the update module. The proposed re-integration module can fully use the outputs of the previous iteration, providing input for the update module for further shadow removal. In this way, the proposed PRNet makes the whole process more concise and only uses 29% network parameters than the best published method. Extensive experiments on the three benchmarks, ISTD, ISTD+, and SRD, demonstrate that our method can effectively remove shadows and achieve superior performance.