Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
It addresses the problem of inconsistent evaluation and dataset bias in shadow-related tasks for computer vision researchers, offering a standardized benchmark to support reproducible research.
This paper provides a unified survey and benchmark for deep learning methods in image and video shadow detection, removal, and generation, revealing inconsistencies in prior reports and limited cross-dataset generalization due to dataset bias.
Shadows, formed by the occlusion of light, play an essential role in visual perception and directly influence scene understanding, image quality, and visual realism. This paper presents a unified survey and benchmark of deep-learning-based shadow detection, removal, and generation across images and videos. We introduce consistent taxonomies for architectures, supervision strategies, and learning paradigms; review major datasets and evaluation protocols; and re-train representative methods under standardized settings to enable fair comparison. Our benchmark reveals key findings, including inconsistencies in prior reports, strong dependence on model design and resolution, and limited cross-dataset generalization due to dataset bias. By synthesizing insights across the three tasks, we highlight shared illumination cues and priors that connect detection, removal, and generation. We further outline future directions involving unified all-in-one frameworks, semantics- and geometry-aware reasoning, shadow-based AIGC authenticity analysis, and the integration of physics-guided priors into multimodal foundation models. Corrected datasets, trained models, and evaluation tools are released to support reproducible research.