LLNet: A deep autoencoder approach to natural low-light image enhancement

In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the success of an operation. Camera sensors are often cost-limited in ability to clearly capture objects without defects from images or videos taken in a poorly-lit environment. The goal in many applications is to enhance the brightness, contrast and reduce noise content of such images in an on-board real-time manner. We propose a deep autoencoder-based approach to identify signal features from low-light images handcrafting and adaptively brighten images without over-amplifying the lighter parts in images (i.e., without saturation of image pixels) in high dynamic range. We show that a variant of the recently proposed stacked-sparse denoising autoencoder can learn to adaptively enhance and denoise from synthetically darkened and noisy training examples. The network can then be successfully applied to naturally low-light environment and/or hardware degraded images. Results show significant credibility of deep learning based approaches both visually and by quantitative comparison with various popular enhancing, state-of-the-art denoising and hybrid enhancing-denoising techniques.

LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work.

/pdf/learning-to-see-in-the-dark-4z0eh24hdb.pdf

Learning to See in the Dark

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work. The results are shown in the supplementary video at this https URL

Low-light image enhancement methods based on classic Retinex model attempt to manipulate the estimated illumination and to project it back to the corresponding reflectance. However, the model does not consider the noise, which inevitably exists in images captured in low-light conditions. In this paper, we propose the robust Retinex model, which additionally considers a noise map compared with the conventional Retinex model, to improve the performance of enhancing low-light images accompanied by intensive noise. Based on the robust Retinex model, we present an optimization function that includes novel regularization terms for the illumination and reflectance. Specifically, we use $\ell _{1}$ norm to constrain the piece-wise smoothness of the illumination, adopt a fidelity term for gradients of the reflectance to reveal the structure details in low-light images, and make the first attempt to estimate a noise map out of the robust Retinex model. To effectively solve the optimization problem, we provide an augmented Lagrange multiplier based alternating direction minimization algorithm without logarithmic transformation. Experimental results demonstrate the effectiveness of the proposed method in low-light image enhancement. In addition, the proposed method can be generalized to handle a series of similar problems, such as the image enhancement for underwater or remote sensing and in hazy or dusty conditions.

/pdf/structure-revealing-low-light-image-enhancement-via-robust-3uw8c91nkr.pdf

Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model

A general method for image contrast enhancement and noise reduction is proposed in this paper. The method is developed especially for enhancing images acquired under very low light conditions where the features of images are nearly invisible and the noise is serious. By applying an improved and effective image de-haze algorithm to the inverted input image, the intensity can be amplified so that the dark areas become bright and the contrast get enhanced. Then, the joint-bilateral filter with the original green component as the edge image is introduced to suppress the noise. Experimental results validate the performance of the proposed approach.

Enhancement and noise reduction of very low light level images

The invention discloses a low-luminance image reinforcing and denoising method. The low-luminance image reinforcing and denoising method includes steps of firstly, judging whether to reinforce and denoise images; secondly, inverting an original image to obtain an image I; thirdly, 0.1% of pixels with highest luminance in dark primary colors of the image I, utilizing the selected pixels as airglow composition A of the image I; fourthly, processing the image I to obtain an image Y through luminance algorithm; fifthly, weakening the image Y to obtain an image CY through parameters; sixthly, subjecting the image CY to median filtering to remove random noise to obtain an image T; seventhly, subjecting the image I to mist elimination to obtain image J by combining the image T and the airglow composition A; eighthly, inverting the image J to an image O; and ninthly, applying the image O and a green channel image G of the original image to a mixed two-sided filter to be subjected to denoising. The low-luminance image reinforcing and denoising method can reinforce luminance of the images and denoise, so that quality of the images can be further improved.

Low-luminance image reinforcing and denoising method

The invention discloses an image/video demisting method based on the combination of a dark primary color and atmospheric scattered light. The method comprises the following specific steps of: 1, inputting an original misty image I into an image processing system of a computer, and acquiring a dark primary color image Idark of the original misty image I; 2, according to the obtained dark primary color image Idark, evaluating the atmospheric light values A, i.e. airR, airG and airB of red, green and blue (RGB) channels of the original image; 3, evaluating the atmospheric scattered light value V (x,y) of the original misty image I; and 4, evaluating a demisted restored image J according to images of the RGB channels of the original misty image I, the atmospheric light values A and the atmospheric scattered light value V to obtain a demisted restored image J finally. According to the image/video demisting method based on the combination of the dark primary color and atmospheric scattered light, a clear demisted image is obtained by calculating the dark primary color image of the original image and restoring the original image with the atmospheric light values and the atmospheric scattered light value.

Luo Lingli

Papers

Enhancement and noise reduction of very low light level images

Low-luminance image reinforcing and denoising method

Image/video demisting method based on combination of dark primary color of atmospheric scattered light