SAM-helps-Shadow:When Segment Anything Model meet shadow removal
This work addresses the need for zero-shot shadow removal in real-world scenarios, representing an incremental improvement by adapting existing models.
The paper tackled the problem of applying image shadow removal to real-world images by adapting the Segment Anything Model (SAM) for zero-shot learning, resulting in a single-stage approach that integrates shadow detection and removal.
The challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-shot learning in this field. In this study, we innovatively adapted the SAM (Segment anything model) for shadow removal by introducing SAM-helps-Shadow, effectively integrating shadow detection and removal into a single stage. Our approach utilized the model's detection results as a potent prior for facilitating shadow detection, followed by shadow removal using a second-order deep unfolding network. The source code of SAM-helps-Shadow can be obtained from https://github.com/zhangbaijin/SAM-helps-Shadow.