Saved in:
Bibliographic Details
Main Authors: Zhao, Minghua, Qin, Xiangdong, Du, Shuangli, Bai, Xuefei, Lyu, Jiahao, Liu, Yiguang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.07753
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910298340851712
author Zhao, Minghua
Qin, Xiangdong
Du, Shuangli
Bai, Xuefei
Lyu, Jiahao
Liu, Yiguang
author_facet Zhao, Minghua
Qin, Xiangdong
Du, Shuangli
Bai, Xuefei
Lyu, Jiahao
Liu, Yiguang
contents Unlike single image task, stereo image enhancement can use another view information, and its key stage is how to perform cross-view feature interaction to extract useful information from another view. However, complex noise in low-light image and its impact on subsequent feature encoding and interaction are ignored by the existing methods. In this paper, a method is proposed to perform enhancement and de-noising simultaneously. First, to reduce unwanted noise interference, a low-frequency information enhanced module (IEM) is proposed to suppress noise and produce a new image space. Additionally, a cross-channel and spatial context information mining module (CSM) is proposed to encode long-range spatial dependencies and to enhance inter-channel feature interaction. Relying on CSM, an encoder-decoder structure is constructed, incorporating cross-view and cross-scale feature interactions to perform enhancement in the new image space. Finally, the network is trained with the constraints of both spatial and frequency domain losses. Extensive experiments on both synthesized and real datasets show that our method obtains better detail recovery and noise removal compared with state-of-the-art methods. In addition, a real stereo image enhancement dataset is captured with stereo camera ZED2. The code and dataset are publicly available at: https://www.github.com/noportraits/LFENet.
format Preprint
id arxiv_https___arxiv_org_abs_2401_07753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space
Zhao, Minghua
Qin, Xiangdong
Du, Shuangli
Bai, Xuefei
Lyu, Jiahao
Liu, Yiguang
Computer Vision and Pattern Recognition
Unlike single image task, stereo image enhancement can use another view information, and its key stage is how to perform cross-view feature interaction to extract useful information from another view. However, complex noise in low-light image and its impact on subsequent feature encoding and interaction are ignored by the existing methods. In this paper, a method is proposed to perform enhancement and de-noising simultaneously. First, to reduce unwanted noise interference, a low-frequency information enhanced module (IEM) is proposed to suppress noise and produce a new image space. Additionally, a cross-channel and spatial context information mining module (CSM) is proposed to encode long-range spatial dependencies and to enhance inter-channel feature interaction. Relying on CSM, an encoder-decoder structure is constructed, incorporating cross-view and cross-scale feature interactions to perform enhancement in the new image space. Finally, the network is trained with the constraints of both spatial and frequency domain losses. Extensive experiments on both synthesized and real datasets show that our method obtains better detail recovery and noise removal compared with state-of-the-art methods. In addition, a real stereo image enhancement dataset is captured with stereo camera ZED2. The code and dataset are publicly available at: https://www.github.com/noportraits/LFENet.
title Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.07753