Colorization

The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing. Each image has detailed annotations: 1 subcategory label, 15 part locations, 312 binary attributes and 1 bounding box. The textual information comes from Reed et al.. They expand the CUB-200-2011 dataset by collecting fine-grained natural language descriptions. Ten single-sentence descriptions are collected for each image. The natural language descriptions are collected through the Amazon Mechanical Turk (AMT) platform, and are required at least 10 words, without any information of subcategories and actions. Source: Fine-grained Visual-textual Representation Learning Image Source: http://www.vision.caltech.edu/visipedia/CUB-200-2011.html

Oxford 102 Flower is an image classification dataset consisting of 102 flower categories. The flowers chosen to be flower commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images. The images have large scale, pose and light variations. In addition, there are categories that have large variations within the category and several very similar categories.

SPair-71k contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations. Source: SPair-71k: A Large-scale Benchmark for Semantic Correspondence Image Source: http://cvlab.postech.ac.kr/research/SPair-71k/

Colorization validation set for unconditional/conditional colorization tasks. Subset of the ImageNet validation images and excludes andy grayscale single-channel images.

SketchyScene is a large-scale dataset of scene sketches to advance research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches. SketchyScene contains more than 29,000 scene-level sketches, 7,000+ pairs of scene templates and photos, and 11,000+ object sketches. All objects in the scene sketches have ground-truth semantic and instance masks. The dataset is also highly scalable and extensible, easily allowing augmenting and/or changing scene composition. Source: SketchyScene: Richly-Annotated Scene Sketches Image Source: [Zoe et al]( SketchyScene: Richly-Annotated Scene Sketches)

The Natural-Color Dataset (NCD) is an image colorization dataset where images are true to their colors. For example, a carrot will have an orange color in most images. Bananas will be either greenish or yellowish. It contains 723 images from the internet distributed in 20 categories. Each image has an object and a white background. Source: https://github.com/saeed-anwar/ColorSurvey#dataset Image Source: https://github.com/saeed-anwar/ColorSurvey

#This dataset provides the VCIP 2020 Grand Challenge on the NIR Image Colorization dataset. ##You can refer to https://jchenhkg.github.io/projects/NIR2RGB_VCIP_Challenge/ for a detailed description of this dataset. ## If you think this dataset is helpful, please feel free to cite our paper: @inproceedings{yang2023cooperative, title={Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation}, author={Yang, Xingxing and Chen, Jie and Yang, Zaifeng}, booktitle={Proceedings of the 31st ACM International Conference on Multimedia}, pages={2409--2417}, year={2023} }

QST contains 1,167 video clips that are cut out from 216 time-lapse 4K videos collected from YouTube, which can be used for a variety of tasks, such as (high-resolution) video generation, (high-resolution) video prediction, (high-resolution) image generation, texture generation, image inpainting, image/video super-resolution, image/video colorization, image/video animating, etc. Each short clip contains multiple frames (from a minimum of 58 frames to a maximum of 1,200 frames, a total of 285,446 frames), and the resolution of each frame is more than 1,024 x 1,024. Specifically, QST consists of a training set (containing 1000 clips, totally 244,930 frames), a validation set (containing 100 clips, totally 23,200 frames), and a testing set (containing 67 clips, totally 17,316 frames). Click here (Key: qst1) to download the QST dataset.

We present a novel Animation CelebHeads dataset (AnimeCeleb) to address an animation head reenactment. Different from previous animation head datasets, we utilize 3D animation models as the controllable image samplers, which can provide a large amount of head images with their corresponding detailed pose annotations. To facilitate a data creation process, we build a semi-automatic pipeline leveraging an open 3D computer graphics software with a developed annotation system. After training with the AnimeCeleb, recent head reenactment models produce high-quality animation head reenactment results, which are not achievable with existing datasets. Furthermore, motivated by metaverse application, we propose a novel pose mapping method and architecture to tackle a cross-domain head reenactment task. During inference, a user can easily transfer one's motion to an arbitrary animation head. Experiments demonstrate the usefulness of the AnimeCeleb to train animation head reenactment models, and the superiority of our cross-domain head reenactment model compared to state-of-the-art methods. Our dataset and code are available at https://github.com/kangyeolk/AnimeCeleb.

MHMD (Modern Historical Movies Dataset) is a dataset for old image colorization, built from historical movies. It consists of 1,353,166 images and 42 labels of eras, nationalities, and garment types for automatic colorization from 147 historical movies or TV series made in modern time.

A real-world stereo video dataset, containing 1200 frame pairs with real-world color and sharpness mismatches caused by beam splitter. Color and sharpness mismatches between views of the stereoscopic 3D video can decrease the overall video quality and may cause viewer discomfort and headaches. To eliminate this problem, there are correction methods that aim to make the views consistent. We propose a new real-world dataset of stereoscopic videos for evaluating color-mismatch-correction methods. We collected it using a beam splitter and three cameras. A beam splitter introduces real-world mismatches between stereopair views. Similar mismatches can appear in stereoscopic movies filmed with a beam-splitter rig. Our approach used a beam splitter to set a zero stereobase between the left camera and the left ground-truth camera, allowing us to create a distorted ground-truth data pair.