Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
While CNNs achieved remarkable progress in shadow detection, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to brightness change. These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias. In this paper, we propose a novel feature decomposition and reweighting scheme to mitigate this intensity bias, in which multi-level integrated features are decomposed into intensity-variant and intensity-invariant components through self-supervision. By reweighting these two types of features, our method can reallocate the attention to the corresponding latent semantics and achieves balanced exploitation of them. Extensive experiments on three popular datasets show that the proposed method outperforms state-of-the-art shadow detectors.
Code (0)
등록된 구현이 없습니다.
Tasks
Shadow DetectionSimilar Papers 제목 키워드 기반
Delving into Dark Regions for Robust Shadow Detection
Shadow detection is a challenging task as it requires a comprehensive understanding of shadow characteristics and global/local illumination conditions. We observe from our experiment that state-of-the-art deep methods te…
Shadow DetectionTest-Time Intensity Consistency Adaptation for Shadow Detection
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep l…
DecoderDiversityScene UnderstandingShadow Detection+1A Shadow Imaging Bilinear Model and Three-branch Residual Network for Shadow Removal
The current shadow removal pipeline relies on the detected shadow masks, which have limitations for penumbras and tiny shadows, and results in an excessively long pipeline. To address these issues, we propose a shadow im…
Image ReconstructionImage Shadow RemovalShadow RemovalUser-Assisted Shadow Removal
This paper presents a novel user-aided method for texture-preserving shadow removal from single images requiring simple user input. Compared with the state-of-the-art, our algorithm offers the most flexible user interact…
Shadow RemovalAdaptive Illumination Mapping for Shadow Detection in Raw Images
Shadow detection methods rely on multi-scale contrast, especially global contrast, information to locate shadows correctly. However, we observe that the camera image signal processor (ISP) tends to preserve more loca…
Shadow Detection