Image Enhancement

The first NER dataset in the field of traffic, which is to extract the characteristics and attributes of the vehicle on the road. * Both flat and overlapped named entities annotation. * Both coarse-grained and fine-grained named entities. * It contains 8 kinds of coarse-grained entities and 12 kinds of fine-grained entities. (It includes 65 vehicle brands and 4793 vehicle models all over the world.)

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

CUHK Image Cropping is a dataset for image cropping. The photos are of varying aesthetic quality and span a variety of image categories, including animal, architecture, human, landscape, night, plant and man-made objects. Each image is manually cropped by three expert photographers (graduate students in art whose primary medium is photography) to form three training sets. There are 1,000 photos in the dataset.

Read all the details about the dataset in our paper "NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement" * We host the dataset in Kaggle: https://www.kaggle.com/datasets/photolab/nilut-3d-lut-dataset * More information in our repo: https://github.com/mv-lab/nilut

A test dataset SICE_Grad image datasets to represent complex mixed over-/under-exposed scenes.

A test dataset SICE_Mix image datasets to represent complex mixed over-/under-exposed scenes.

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.

To provide ground truth supervision for video consistency modeling, we build up a high-quality dynamic OLAT dataset. Our capture system consists of a light stage setup with 114 LED light sources and Phantom Flex4K-GS camera (global shutter, stationary 4K ultra-high-speed camera at 1000 fps), resulting in dynamic OLAT imageset recording at 25 fps using the overlapping method. Our dynamic OLAT dataset provides sufficient semantic, temporal and lighting consistency supervision to train our neural video portrait relighting scheme, which can generalize to in-the-wild scenarios.

A high-quality captured dataset for object relighting. Covering a wide range of geometry and material.

A high-quality synthetic dataset for object relighting. Covering a wide range of geometry and material.

The first ultra-high-definition image demoireing dataset, consisting of 4,500 4K resolution training pairs and 500 standard 4K resolution validation pairs.

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.

A large film style dataset

We establish the first large benchmark called IRBFD to facilitate the research in the area of nonuniformity correction and infrared UAV target detection, which consists of 50,000 manually labeled infrared images with various nonuniformity levels, multi-scale UAV targets and rich backgrounds with target annotations.

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.

PolarRR is a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images. Source: Polarized Reflection Removal with Perfect Alignment in the Wild

The datasets used in our WACV paper High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer. StainDoc is a newly created document stain dataset. StainDoc_mark and StainDoc_seal are synthetic datasets.

A pioneering dataset for vignette removal. Vigset includes 983 pairs of both vignetting and vignetting-free high-resolution (5340×3697) real-world images under various conditions.

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!!!

Underwater Image Enhancement Dataset