https://scholars.lib.ntu.edu.tw/handle/123456789/633894
Title: | Missing Recovery: Single Image Reflection Removal Based on Auxiliary Prior Learning | Authors: | WEI-TING CHEN Chen, Kuan Yu Chen, I. Hsiang Fang, Hao Yu JIAN-JIUN DING SY-YEN KUO |
Keywords: | auxiliary prior learning | dark channel loss | missing recovery | Single image reflection removal | Issue Date: | 1-Jan-2023 | Journal Volume: | 32 | Source: | IEEE Transactions on Image Processing | Abstract: | Photographs taken through a glass window are susceptible to disturbances due to reflection. Therefore, single image reflection removal is crucial to image quality enhancement. In this paper, a novel learning architecture that can address this ill-posed problem is proposed. First, a novel reflection removal pipeline was designed to reconstruct the missing information caused by the camera imaging process using the proposed missing recovery network. Second, to address the issues in existing reflection removal strategies, we revisit several auxiliary priors and integrate them by defining an energy function. To solve the energy function, a convolutional neural network-based optimization scheme was proposed. Finally, we investigated the dark channel responses of reflection and clean images and found an interesting way to distinguish between these two types of images. We prove this property mathematically and propose a novel loss function called dark channel loss to improve performance. Experiments show that the proposed method outperforms state-of-the-art reflection removal methods both quantitatively and qualitatively. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/633894 | ISSN: | 10577149 | DOI: | 10.1109/TIP.2022.3230544 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.