Info-icon.png We have moved to https://openmodeldb.info/. This new site has a tag and search system, which will make finding the right models for you much easier! If you have any questions, ask here: https://discord.gg/cpAUpDK

Difference between revisions of "Datasets"

From Upscale Wiki
Jump to navigation Jump to search
Line 33: Line 33:
 
| [https://yingqianwang.github.io/Flickr1024/ Flickr1024] || no ||  Flickr1024 is a large stereo dataset, which consists of 1024 high-quality images pairs and covers diverse senarios. This dataset can be employed for stereo image super-resolution (SR).  
 
| [https://yingqianwang.github.io/Flickr1024/ Flickr1024] || no ||  Flickr1024 is a large stereo dataset, which consists of 1024 high-quality images pairs and covers diverse senarios. This dataset can be employed for stereo image super-resolution (SR).  
 
|-
 
|-
| [https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar Flickr2K] || no || Huge dataset that is being used to train a lot of models. |}
+
| [https://cv.snu.ac.kr/research/EDSR/Flickr2K.tar Flickr2K] || no || Huge dataset that is being used to train a lot of models.  
 +
|}

Revision as of 20:07, 18 August 2019

A collection of different sources for Datasets.

Name Price Description
quixel megascans yes Discover a world of unbounded creativity. Explore a massive asset library, and Quixel’s powerful tools, plus free in-depth tutorials and resources.
Adobe Stock yes Stock photos, royalty-free images, graphics, vectors & videos
Pexels no Free stock photos you can use everywhere. ✓ Free for commercial use ✓ No attribution required
Poliigon jein - todo -
Textures.com ? Textures for 3D, Graphic Design and Photoshop 15 Free downloads every day!
texturehaven no 100% Free High Quality Textures for Everyone
Gustave Doré's 1866 Bible Illustrations no High-Res Scans of Gustave Doré's 1866 Bible Illustrations
texturelib no Library of quality high resolution textures. Free for personal and commercial use.
Vimeo-90k no This dataset consists of 89,800 video clips downloaded from vimeo.com, which covers large variaty of scenes and actions. It is designed for the following four video processing tasks: temporal frame interpolation, video denoising, video deblocking, and video super-resolution.
Triplet (for temporal frame interpolation) no The triplet dataset consists of 73,171 3-frame sequences with a fixed resolution of 448 x 256, extracted from 15K selected video clips from Vimeo-90k. This dataset is designed for temporal frame interpolation.
Septuplets no The septuplet dataset consists of 91,701 7-frame sequences with fixed resolution 448 x 256, extracted from 39K selected video clips from Vimeo-90k. This dataset is designed to video denoising, deblocking, and super-resolution.
falcoon300 no LyonHrt: As it has been mentioned, here is the almost complete works of falcoon, as used in the falcoon300 model, this has a selection of 1233 images from original source, I should add there are some scantly clad woman, so nsfw lol.
Danbooru2018 no Danbooru2018 is a large-scale anime image database with 3.33m+ images annotated with 99.7m+ tags; it can be useful for machine learning purposes such as image recognition and generation.
Flickr1024 no Flickr1024 is a large stereo dataset, which consists of 1024 high-quality images pairs and covers diverse senarios. This dataset can be employed for stereo image super-resolution (SR).
Flickr2K no Huge dataset that is being used to train a lot of models.