Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space

TL;DR

This paper introduces a novel stereo image enhancement and de-noising method that leverages low-frequency information and cross-view interactions to improve detail recovery and noise suppression in low-light conditions.

Contribution

It proposes a low-frequency information enhanced module and a cross-channel spatial context mining module for simultaneous enhancement and de-noising in stereo images.

Findings

Outperforms state-of-the-art methods in detail recovery.

Effectively suppresses noise in low-light stereo images.

Validated on synthesized and real datasets, including a newly captured dataset.

Abstract

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.