Low-Light Image Enhancement

The LOL dataset is composed of 500 low-light and normal-light image pairs and divided into 485 training pairs and 15 testing pairs. The low-light images contain noise produced during the photo capture process. Most of the images are indoor scenes. All the images have a resolution of 400×600. Source: Unsupervised Real-world Low-light Image Enhancement with Decoupled Networks Image Source: https://daooshee.github.io/BMVC2018website/

The 3DMATCH benchmark evaluates how well descriptors (both 2D and 3D) can establish correspondences between RGB-D frames of different views. The dataset contains 2D RGB-D patches and 3D patches (local TDF voxel grid volumes) of wide-baselined correspondences. The pixel size of each 2D patch is determined by the projection of the 0.3m3 local 3D patch around the interest point onto the image plane. Source: 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

The See-in-the-Dark (SID) dataset contains 5094 raw short-exposure images, each with a corresponding long-exposure reference image. Images were captured using two cameras: Sony α7SII and Fujifilm X-T2.

The Annotated Facial Landmarks in the Wild (AFLW) is a large-scale collection of annotated face images gathered from Flickr, exhibiting a large variety in appearance (e.g., pose, expression, ethnicity, age, gender) as well as general imaging and environmental conditions. In total about 25K faces are annotated with up to 21 landmarks per image. Source: Nose, Eyes and Ears: Head Pose Estimation by Locating Facial Keypoints

• Visible-infrared Paired Dataset for Low-light Vision * 30976 images (15488 pairs) * 24 dark scenes, 2 daytime scenes * Support for image-to-image translation (visible to infrared, or infrared to visible), visible and infrared image fusion, low-light pedestrian detection, and infrared pedestrian detection * (The original image and video pairs (before registration) of LLVIP are also released!)

DICM is a dataset for low-light enhancement which consists of 69 images collected with commercial digital cameras. Source: Deep Retinex Decomposition for Low-Light Enhancement Image Source: GLADNet: Low-Light Enhancement Network with Global Awareness

The Exclusively Dark (ExDARK) dataset is a collection of 7,363 low-light images from very low-light environments to twilight (i.e 10 different conditions) with 12 object classes (similar to PASCAL VOC) annotated on both image class level and local object bounding boxes. Source: https://github.com/cs-chan/Exclusively-Dark-Image-Dataset

The MIT-Adobe FiveK dataset consists of 5,000 photographs taken with SLR cameras by a set of different photographers. They are all in RAW format; that is, all the information recorded by the camera sensor is preserved. We made sure that these photographs cover a broad range of scenes, subjects, and lighting conditions. We then hired five photography students in an art school to adjust the tone of the photos. Each of them retouched all the 5,000 photos using a software dedicated to photo adjustment (Adobe Lightroom) on which they were extensively trained. We asked the retouchers to achieve visually pleasing renditions, akin to a postcard. The retouchers were compensated for their work. This dataset was collected for our project on learning photographic adjustments. When using images from this dataset, please cite this dataset using the following BibTeX: @inproceedings{fivek, author = "Vladimir Bychkovsky and Sylvain Paris and Eric Chan and Fr{\'e}do Durand", title = "Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs", booktitle = "The Twenty-Fourth IEEE Conference on Computer Vision and Pattern Recognition", year = "2011" } Source: https://data.csail.mit.edu/graphics/fivek/ Image source: https://data.csail.mit.edu/graphics/fivek/

LOL-v2-real contains 689 low-/normal-light image pairs for training and 100 pairs for testing.

This is the low-light image enhancement dataset collected by the CVPR 2018 paper "Seeing Motion in the Dark".

The real captured dataset of LOL contains 500 low/normallight image pairs. Most low-light images are collected by changing exposure time and ISO, while other configurations of the cameras are fixed. We capture images from a variety of scenes, e.g., houses, campuses, clubs, streets. Since camera shaking, object movement, and lightness changing may cause misalignment between the image pairs, inspired by [41], a three-step shooting strategy is used to eliminate such misalignments between the image pairs in our dataset. For one scene, we first shoot two normal-light images $N_1$ and $N_2$. Then, we change the exposure time and ISO to capture a series of low-light images. Finally, we set the exposure time and ISO back to shoot another two normal-light images $N_3$ and $N_4$. The average of $N_i (i = 1,2,3,4)$ is treated as the ground-truth $G=\frac{1}{4}\sum^4_{i=1}N_i$. Then, we check whether there is object or camera movement. Specifically, the misalignment for these normal-light images is measured by $M=\frac{1}{4}\sum^4_{i=1}MSE(Ni, G)$. If M > 0.1, we abandon the corresponding pair. These raw images are resized to 400 × 600 and converted to Portable Network Graphics format. The dataset is publicly available.

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

To make synthetic images match the property of real dark photography, we analyze the illumination distribution of low-light images. We collect 270 low-light images from public MEF [42], NPE [6], LIME [8], DICM [43], VV,2 and Fusion [44] dataset, transform the imagesT into YCbCr channel and calculate the histogram of Y channel. We also collect 1000 raw images from RAISE [45] as normal-light images and calculate the histogram of Y channel in YCbCr. Raw images contain more information than the converted results. For raw images, all operations used to generate pixel values are performed in one step on the base data, making the result more accurate. 1000 raw images in RAISE [45] are used to synthesize low-light images. Interface provided by Adobe Lightroom is used and we try different kinds of parameters to make the histogram of Y channel fit the result in low-light images. Final parameter configuration can be found in the supplementary material. The illumination distribution of synthetic images matches that of low-light images. Finally, we resize these raw images to 400 × 600 and convert them to Portable Network Graphics format.

Multi-exposure image fusion (MEF) is considered an effective quality enhancement technique widely adopted in consumer electronics, but little work has been dedicated to the perceptual quality assessment of multi-exposure fused images. In this paper, we first build an MEF database and carry out a subjective user study to evaluate the quality of images generated by different MEF algorithms. There are several useful findings. First, considerable agreement has been observed among human subjects on the quality of MEF images. Second, no single state-of-the-art MEF algorithm produces the best quality for all test images. Third, the existing objective quality models for general image fusion are very limited in predicting perceived quality of MEF images. Motivated by the lack of appropriate objective models, we propose a novel objective image quality assessment (IQA) algorithm for MEF images based on the principle of the structural similarity approach and a novel measure of patch structural consistency. Our experimental results on the subjective database show that the proposed model well correlates with subjective judgments and significantly outperforms the existing IQA models for general image fusion. Finally, we demonstrate the potential application of the proposed model by automatically tuning the parameters of MEF algorithms

LoLi-Phone is a large-scale low-light image and video dataset for Low-light image enhancement (LLIE). The images and videos are taken by different mobile phones' cameras under diverse illumination conditions.

The dataset collected by the paper Seeing Dynamic Scene in the Dark: High-Quality Video Dataset with Mechatronic Alignment, ICCV 2021

Seeing Dynamic Scene in the Dark: High-Quality Video Dataset with Mechatronic Alignment

Original SID dataset is introduced in "Learning to See in the Dark". The subset of SID dataset captured by Sony α7S II camera is adopted for evaluation. There are 2697 short-long-exposure RAW image pairs. To make this dataset more challenging, we converted the RAW format images to sRGB images with no gamma correction, which resulted in images becoming extremely dark.

The goal of this project is to present two new datasets that seek to expand the capability of the Learning to See in the Dark Low-light enhancement CNN for the Canon 6D DSLR, and explore how the network performs when modified in various ways, both pruning it and making it deeper. The original paper Learning to See in the Dark was published in CVPR 2018, by Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun.

LLNeRF Dataset is a real-world dataset as a benchmark for model learning and evaluation. To obtain real low-illumination images with real noise distributions, photos are taken at nighttime outdoor scenes or low-light indoor scenes containing diverse objects. Since the ISP operations are device dependent and the noise distributions across devices are also different, the data is collected using a mobile phone camera and a DSLR camera to enrich the diversity of the dataset.

Dataset release for the BMVC 2021 Paper "Few-Shot Domain Adaptation for Low Light RAW Image Enhancement" Abstract: Enhancing practical low light raw images is a difficult task due to severe noise and color distortions from short exposure time and limited illumination. Despite the success of existing Convolutional Neural Network (CNN) based methods, their performance is not adaptable to different camera domains. In addition, such methods also require large datasets with short-exposure and corresponding long-exposure ground truth raw images for each camera domain, which is tedious to compile. To address this issue, we present a novel few-shot domain adaptation method to utilize the existing source camera labeled data with few labeled samples from the target camera to improve the target domain’s enhancement quality in extreme low-light imaging. Our experiments show that only ten or fewer labeled samples from the target camera domain are sufficient to achieve similar or better enhancement performance than training a model with a large labeled target camera dataset. To support research in this direction, we also present a new low-light raw image dataset captured with a Nikon camera, comprising short-exposure and their corresponding long-exposure ground truth images. The code is available at https://val.cds.iisc.ac.in/HDR/BMVC21/index.html.

We introduce low-light image enhancement benchmark dataset “Low-light Images of Streets (LoLI-Street),” which contains three subsets: train, validation, and test. The train and validation sets consist of 30k and 3k paired low-light and high-light images, respectively, and the real low-light test set (RLLT) contains 1k images under real-world low-light conditions, totaling 33k images. 1. Download LoLI-Street Dataset 2. Read Full Paper ## Citation: If you use the dataset, please cite our paper: python @InProceedings{Islam_2024_ACCV, author = {Islam, Md Tanvir and Alam, Inzamamul and Woo, Simon S. and Anwar, Saeed and Lee, IK Hyun and Muhammad, Khan}, title = {LoLI-Street: Benchmarking Low-light Image Enhancement and Beyond}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1250-1267}} Thank you!

Introduced by Khan. et al. Divide and conquer: Ill-light image enhancement via hybrid deep network https://www.sciencedirect.com/science/article/abs/pii/S0957417421004759 The images captured under ill-lighting conditions, such as above lit, low-lit, back-lit, front-lit, and combination of them, with the robust exposure variation, suffer from various artefacts due to non-uniform lighting conditions. DILCOD consisting of 1000 training images (500-low light and 500 normal light) and 38 test images with respective ground truth images to evaluate the performance of our network. The captured test images are dividedequally into test-data-samples-A and data-samples B with corresponding ground-truth images. Images in test-data-sample-A are captured with mainly front diverse exposure variation using low light in the background. In contrast, theimages in the test-data-sample-B consist of back-lit images in which the background contains a point light source, but the front region is almost under-exposed. We use diverse lighting conditions to capture the scenes by using (CREVIS MV-CS30G with 8 mm lens) cameras in our capturing system. We utilized state of the art multi-lighting system to fulfil this challenging task. The camera’s baseline varies at 30 cm, with each camera at 30 degree. The images are captured using point light sources, and ground truth images are captured with a sufficiently large light with the best available visual appearance. You are free to use train-test pairs __ GTs__, and make new combinations! Cheers!!!