Voxel51/Set5

Set5数据集包含5张图像（“baby”、“bird”、“butterfly”、“head”、“woman”），这些图像常用于测试图像超分辨率模型的性能。该数据集由Bevilacqua、Marco、Roumy、Antoine、Guillemot、Christine和Alberi-Morel、Marie-Line策划，语言为英语，许可证为其他。

The Set5 dataset is a dataset consisting of 5 images (“baby”, “bird”, “butterfly”, “head”, “woman”) commonly used for testing performance of Image Super-Resolution models. The dataset was created by Bevilacqua, Marco et al., with English as the language and other as the license type. The main use of the dataset is super-resolution.

原始信息汇总

Set5 数据集概述

数据集描述

Set5 数据集包含 5 张图像（“baby”, “bird”, “butterfly”, “head”, “woman”），通常用于测试图像超分辨率模型的性能。

基本信息

• 样本数量: 135
• 语言: 英语 (en)
• 许可证: 其他 (other)
• 任务类别: 图像到图像 (image-to-image)
• 标签: fiftyone, image, superresolution

数据集来源

• 仓库: https://github.com/ChaofWang/Awesome-Super-Resolution/blob/master/dataset.md
• 论文: Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding
• 主页: https://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html

用途

用于超分辨率任务。

引用

bibtex @inproceedings{bevilacqua2012low, title={Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding}, author={Bevilacqua, Marco and Roumy, Antoine and Guillemot, Christine and Alberi-Morel, Marie-Line}, booktitle={Proceedings of the British Machine Vision Conference (BMVC)}, year={2012} }