Abandoning the Bayer-Filter to See in the Dark

TL;DR

This paper introduces a novel low-light image enhancement method that fuses colored raw data with synthesized monochrome raw images generated by a deep neural network, improving visibility in dark environments.

Contribution

It presents a De-Bayer-Filter simulator and a fusion network with channel-wise attention, along with a new dataset of paired monochrome and color raw images for training.

Findings

Significant improvement in low-light image quality using raw data fusion.

Effective use of a deep learning-based De-Bayer-Filter simulator.

Enhanced feature interaction through channel-wise attention in fusion process.

Abstract

Low-light image enhancement - a pervasive but challenging problem, plays a central role in enhancing the visibility of an image captured in a poor illumination environment. Due to the fact that not all photons can pass the Bayer-Filter on the sensor of the color camera, in this work, we first present a De-Bayer-Filter simulator based on deep neural networks to generate a monochrome raw image from the colored raw image. Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome raw data. Channel-wise attention is also introduced to the fusion process to establish a complementary interaction between features from colored and monochrome raw images. To train the convolutional networks, we propose a dataset with monochrome and color raw pairs named Mono-Colored Raw paired dataset (MCR) collected by using a monochrome camera without Bayer-Filter and a color camera with Bayer-Filter. The proposed pipeline take advantages of the fusion of the virtual monochrome and the color raw images and our extensive experiments indicate that significant improvement can be achieved by leveraging raw sensor data and data-driven learning.