RFFNet: Towards Robust and Flexible Fusion for Low-Light Image Denoising

Qiang Wang, Yuning Cui, Yawen Li, paulruan, zhuben, Wenqi Ren

Abstract:

Low-light environments will introduce high-intensity noise into images. Containing fine details with reduced noise, near-infrared/flash images can serve as guidance to facilitate noise removal.
However, existing fusion-based methods fail to effectively suppress artifacts caused by inconsistency between guidance/noisy image pairs and do not fully excavate the useful information contained in guidance images. In this paper, we propose a robust and flexible fusion network (RFFNet) for low-light image denoising. Specifically, we present a multi-scale inconsistency calibration module to address inconsistency before fusion by first mapping the guidance features to multi-scale spaces and calibrating them with the aid of pre-denoising features in a coarse-to-fine manner. Furthermore, we develop a dual-domain adaptive fusion module to adaptively extract useful high-/low-frequency signals from the guidance features and then highlight the informative frequencies.
Extensive experimental results demonstrate that our method achieves state-of-the-art performance on NIR-guided RGB image denoising and flash-guided no-flash image denoising.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Content] Multimodal Fusion

Relevance To Conference: This paper is about the multi-modal image fusion in low-light environments, such as visible and near-infrared images fusion, and non-flash and flash images fusion. The objective is to enhance the target image by using the guidance information, making it more visually appealing or suitable for high-level tasks. Such technique is commonly employed in multi-sensor imaging systems, including smartphone camera modules, surveillance devices, and other multimedia applications.

Submission Number: 1459