└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Image Processing Datasets (Low-Level Vision Datasets) 2 | 3 | A list of image processing datasets in regions of brightening, HDR, color enhancement and inpainting. 4 | 5 | ## Dehazing 6 | * Waterloo IVC Dehazed Image Database [[PDF]](http://ieeexplore.ieee.org/document/7351475/) [[WEB]](http://ivc.uwaterloo.ca/database/Dehaze/Dehaze-Database.php) 7 | * Perceptual evaluation of single image dehazing algorithms (ICIP'15), Kede Ma, Wentao Liu and Zhou Wang. 8 | * FRIDA dataset [[WEB]](http://perso.lcpc.fr/tarel.jean-philippe/bdd/frida.html) 9 | * D-hazy [[PDF]](http://www.meo.etc.upt.ro/AncutiProjectPages/D_Hazzy_ICIP2016/D_HAZY_ICIP2016.pdf) [[WEB]](http://www.meo.etc.upt.ro/AncutiProjectPages/D_Hazzy_ICIP2016/) 10 | * CHIC [[PDF]](https://link.springer.com/chapter/10.1007/978-3-319-33618-3_12) 11 | * A Color Image Database for Haze Model and Dehazing Methods Evaluation 12 | * HazeRD [[PDF]](https://ieee-dataport.org/documents/hazerd-outdoor-dataset-dehazing-algorithms) 13 | * HazeRD: an outdoor dataset for dehazing algorithms 14 | * I-HAZE : a dehazing benchmark with real hazy and haze-free outdoor images [[PDF]](https://arxiv.org/abs/1804.05091) 15 | * O-HAZE : a dehazing benchmark with real hazy and haze-free out 16 | door images [[PDF]](https://arxiv.org/abs/1804.05101) 17 | * RESIDE: A Benchmark for Single Image Dehazing [[WEB]](https://sites.google.com/view/reside-dehaze-datasets) 18 | 19 | ## Deblurring (sharpening) 20 | * Understanding and evaluating blind deconvolution algorithms (CVPR'09) [[PDF]](https://ieeexplore.ieee.org/document/5206815) 21 | * Edge-based blur kernel estimation using patch priors [[PDF]](https://ieeexplore.ieee.org/document/6528301/) 22 | * Benchmarking blind deconvolution with a real-world database (ECCV'12) [[PDF]](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.379.1398&rep=rep1&type=pdf) 23 | * A Comparative Study for Single Image Blind Deblurring (CVPR'16) [[WEB]](http://vllab.ucmerced.edu/wlai24/cvpr16_deblur_study/) 24 | 25 | ## Denoising 26 | * Smartphone Image Denoising Dataset [[PDF]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Abdelhamed_A_High-Quality_Denoising_CVPR_2018_paper.pdf) 27 | * A High-Quality Denoising Dataset for Smartphone Cameras (CVPR2018), Abdelrahman Abdelhamed, Stephen Lin, Michael S. Brown. 28 | * Darmstadt Noise Dataset [[PDF]](https://download.visinf.tu-darmstadt.de/papers/2017-cvpr-ploetz-benchmarking_denoising_algorithms-preprint.pdf) [[WEB]](https://noise.visinf.tu-darmstadt.de/) 29 | * Benchmarking Denoising Algorithms with Real Photographs (CVPR2017), Tobias Plötz and Stefan Roth. 30 | * PolyU Dataset [[PDF]](https://arxiv.org/pdf/1804.02603.pdf) [[WEB]](https://github.com/csjunxu/PolyU-Real-World-Noisy-Images-Dataset) 31 | * Real-world Noisy Image Denoising: A New Benchmark (Arxiv2017), Jun Xu, Hui Li, Zhetong Liang, David Zhang, and Lei Zhang. 32 | * RENOIR Dataset [[PDF]](https://arxiv.org/pdf/1409.8230.pdf) [[WEB]](http://ani.stat.fsu.edu/~abarbu/Renoir.html) 33 | * A Dataset for Real Low-Light Image Noise Reduction (Arxiv2014), J. Anaya, A. Barbu. 34 | * Holistic Dataset [[PDF]](http://snam.ml/assets/ccnoise_cvpr16/ccnoise_cvpr16.pdf) [[WEB]](http://snam.ml/research/ccnoise) 35 | * A Holistic Approach to Cross-Channel Image Noise Modeling and its Application to Image Denoising (CVPR2016), Seonghyeon Nam, Youngbae Hwang, Yasuyuki Matsushita, Seon Joo Kim. 36 | 37 | ## Image Deraining 38 | ### Rain streak removal 39 | #### Single image deraining 40 | * Rain Streak Database [[DATASET]](http://www1.cs.columbia.edu/CAVE/projects/rain_ren/rain_ren.php)[[PDF]](http://www1.cs.columbia.edu/CAVE/publications/pdfs/Garg_TOG06.pdf) 41 | * Photorealistic rendering of rain streaks 42 | * Rain12 [[DATASET]](http://yu-li.github.io/paper/li_cvpr16_rain.zip)[[PDF]](https://ieeexplore.ieee.org/abstract/document/7934436/) 43 | * Single Image Rain Streak Decomposition Using Layer Priors 44 | * Rain100L and Rain100H [[DATASET]](http://www.icst.pku.edu.cn/struct/Projects/joint_rain_removal.html)[[PDF](https://ieeexplore.ieee.org/document/8099666)] 45 | * Deep Joint Rain Detection and Removal From a Single Image 46 | * Rain800 [[DATASET](https://github.com/hezhangsprinter/ID-CGAN)][[PDF](https://arxiv.org/abs/1701.05957)] 47 | * ID_CGAN:Image De-raining Using a Conditional Generative Adversarial Network 48 | * Rain1400 [[DATASET](https://xueyangfu.github.io/projects/cvpr2017.html)][[PDF](http://openaccess.thecvf.com/content_cvpr_2017/papers/Fu_Removing_Rain_From_CVPR_2017_paper.pdf)] 49 | * Removing rain from single images via a deep detail network 50 | * Rain1200 [[DATASET]](https://github.com/hezhangsprinter/DID-MDN)[[PDF](https://arxiv.org/abs/1802.07412)] 51 | * Density-aware Single Image De-raining using a Multi-stream Dense Network 52 | * Heavy Rain Dataset [[DATASET](https://drive.google.com/file/d/1rFpW_coyxidYLK8vrcfViJLDd-BcSn4B/view)][[PDF](http://export.arxiv.org/pdf/1904.05050)] 53 | * Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning 54 | * SPANet Dataset [[DATASET](https://stevewongv.github.io/derain-project.html)][[PDF](https://arxiv.org/pdf/1904.01538.pdf)] 55 | * Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset 56 | 57 | #### Video rain removal 58 | * MS-CSC-Rain-Streak-Removal [[WEB]](https://github.com/MinghanLi/MS-CSC-Rain-Streak-Removal) 59 | * Video Rain Streak Removal By Multiscale ConvolutionalSparse Coding 60 | 61 | ### Rain drop removal 62 | * Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR'18) [[WEB]](https://rui1996.github.io/raindrop/raindrop_removal.html) 63 | 64 | ## Inpainting 65 | * Image Inpainting [[WEB]](http://chalearnlap.cvc.uab.es/dataset/30/description/) 66 | * 2018 Chalearn Looking at People Satellite Workshop ECCV 67 | 68 | ## Brightening 69 | * VIP-LowLight Dataset [[WEB]](https://uwaterloo.ca/vision-image-processing-lab/research-demos/vip-lowlight-dataset) 70 | * Eight Natural Images Captured in Very Low-Light Conditions, Audrey Chung. 71 | * ReNOIR [[PDF]](https://arxiv.org/abs/1409.8230) [[WEB]](http://ani.stat.fsu.edu/~abarbu/Renoir.html) 72 | * RENOIR - A Dataset for Real Low-Light Image Noise Reduction (JVCIR2018), Josue Anaya, Adrian Barbu 73 | * Raw Image Low-Light Object Dataset [[WEB]](https://wiki.qut.edu.au/display/cyphy/Datasets) 74 | * Dan Richards, James Sergeant, Michael Milford, Peter Corke 75 | * Learning to See in the Dark [[PDF]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Learning_to_See_CVPR_2018_paper.pdf) [[WEB]](http://vladlen.info/publications/learning-see-dark/) 76 | * Learning to See in the Dark (CVPR2018), Chen Chen, Qifeng Chen, Jia Xu, Vladlen Koltun. 77 | * ExDARK [[PDF]](https://arxiv.org/abs/1805.11227) 78 | * Getting to Know Low-light Images with The Exclusively Dark Dataset (Submitted to CVIU), Yuen Peng Loh, Chee Seng Chan. 79 | 80 | ## Color Enhancement 81 | * MIT FiveK dataset [[PDF]](https://people.csail.mit.edu/sparis/publi/2011/cvpr_auto/Bychkovsky_11_Learning_Photo_Adjustment.pdf) [[WEB]](https://data.csail.mit.edu/graphics/fivek/) 82 | * Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs (CVPR2011), Vladimir Bychkovsky, Sylvain Paris and Eric Chan, Fredo Durand. 83 | * LRAICE-Dataset [[PDF]](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Yan_A_Learning-to-Rank_Approach_2014_CVPR_paper.pdf) [[WEB]]() 84 | * A Learning-to-Rank Approach for Image Color Enhancement (CVPR2014), Jianzhou Yan, Stephen Lin, Sing Bing Kang, Xiaoou Tang. 85 | * DPED dataset [[PDF]](https://arxiv.org/abs/1704.02470) [[WEB]](http://people.ee.ethz.ch/~ihnatova/) 86 | * DSLR-quality photos on mobile devices with deep convolutional networks (ICCV2017), A. Ignatov, N. Kobyshev, K. Vanhoey, R. Timofte, L. Van Gool. 87 | * The 500px Dataset [[PDF]](https://www.microsoft.com/en-us/research/uploads/prod/2018/01/Exposure.pdf) 88 | * Exposure: A White-Box Photo Post-Processing Framework (TOG2018), Yuanming Hu, Hao He, Chenxi Xu, Baoyuan Wang, Stephen Lin. 89 | 90 | ## Super Resolution 91 | * Train91 [[PDF]](http://www.columbia.edu/~jw2966/papers/YWHM10-TIP.pdf) [[WEB]](http://www.ifp.illinois.edu/~jyang29/ScSR.htm) 92 | * Image Super-Resolution via Sparse Representation (TIP2010), Jianchao Yang, John Wright, Thomas Huang, and Yi Ma. 93 | * Set5 [[PDF]](http://www.vision.ee.ethz.ch/~timofter/publications/Timofte-ICCV-2013.pdf) [[WEB]](http://www.vision.ee.ethz.ch/~timofter/ICCV2013_ID1774_SUPPLEMENTARY/index.html) 94 | * Anchored Neighborhood Regression for Fast Example-Based Super-Resolution (ICCV2013), Radu Timofte, Vincent De Smet, and Luc Van Gool. 95 | * Set14 [[PDF]](http://www.cs.technion.ac.il/~elad/publications/conferences/2010/ImageScaleUp_LNCS.pdf) 96 | * On Single Image Scale-Up Using Sparse-Representations (International conference on curves and surfaces 2010), Zeyde, Roman and Elad, Michael and Protter, Matan. 97 | * B100 [[PDF]](https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/papers/amfm_pami2010.pdf) [[WEB]](https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html) 98 | * Contour Detection and Hierarchical Image Segmentation (TPAMI2011), P. Arbelaez, M. Maire, C. Fowlkes and J. Malik. 99 | * Urban100 [[PDF]](https://uofi.box.com/shared/static/8llt4ijgc39n3t7ftllx7fpaaqi3yau0.pdf) [[WEB]](https://sites.google.com/site/jbhuang0604/publications/struct_sr) 100 | * Single Image Super-Resolution from Transformed Self-Exemplars (CVPR2015), Jia-Bin Huang, Abhishek Singh, and Narendra Ahuja. 101 | * DIV2K [[PDF]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014884) [[WEB]](https://data.vision.ee.ethz.ch/cvl/DIV2K/) 102 | * NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study (CVPRW2017), Eirikur Agustsson, Radu Timofte. 103 | * LIVE [[PDF]](https://ieeexplore.ieee.org/document/1709988) [[WEB]](http://live.ece.utexas.edu/research/quality/subjective.htm) 104 | * A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms (TIP2006), H.R. Sheikh, M.F. Sabir and A.C. Bovik. 105 | * Super-Resolution Erlangen (SupER) [[PDF]](https://arxiv.org/pdf/1709.04881.pdf) [[WEB]](https://superresolution.tf.fau.de/) 106 | * Benchmarking Super-Resolution Algorithms on Real Data (Arxiv2017), Thomas Köhler, Michel Bätz, Farzad Naderi, André Kaup, Andreas Maier, and Christian Riess. 107 | 108 | # Acknowledgements 109 | The list is maintained by Wenjing Wang, Dejia Xu, Qingyang Li, Wenhan Yang from [STRUCT Group](http://www.icst.pku.edu.cn/struct/struct.html) at PKU. More details can refer to [website](https://github.com/daooshee/Image-Processing-Datasets/blob/master/README.md). 110 | --------------------------------------------------------------------------------