While often referred to as Set14 , it is an extension of the earlier Set5 dataset. It consists of 14 images with varying textures and structures used to test how well algorithms can upscale images while preserving sharp edges.
You will see this image and its associated paper cited in almost every major Super-Resolution study, including those for SRCNN , VDSR , and EDSR , as it serves as a standard for comparing Peak Signal-to-Noise Ratio ( PSNR ) and Structural Similarity Index ( SSIM ) values. AI responses may include mistakes. Learn more Set_41_IMG_29_491615812a62cdcd56c55b1e29d25768.jpg
On Single Image Scale-Up Using Sparse-Representations of Raw Image Patches Authors: Roman Zeyde, Michael Elad, and Matan Protter While often referred to as Set14 , it
The image filename is a specific identifier from the Set14 dataset , a widely used benchmark in Single Image Super-Resolution (SISR) research. AI responses may include mistakes