ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal

arXiv:2309.06670v3 Announce Type: replace
Abstract: Document shadow is a common issue that arises when capturing documents using mobile devices, which significantly impacts readability. Current methods encounter various challenges, including inaccurate detection of shadow masks and estimation of illumination. In this paper, we propose ShaDocFormer, a Transformer-based architecture that integrates traditional methodologies and deep learning techniques to tackle the problem of document shadow removal. The ShaDocFormer architecture comprises two components: the Shadow-attentive Threshold Detector (STD) and the Cascaded Fusion Refiner (CFR). …

abstract architecture arxiv challenges cs.cv current detection devices document documents fusion impacts issue masks mobile mobile devices paper readability shadow threshold transformer type