Images

Set5

Introduced by Marco Bevilacqua et al. in Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding

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.

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Super-Resolution	Set5 - 2x upscaling	HAT-L
Image Super-Resolution	Set5 - 3x upscaling	HAT-L
Image Super-Resolution	Set5 - 8x upscaling	MFSRCNN
Image Super-Resolution	Set5 - 4x upscaling	DRCT-L
Blind Super-Resolution	Set5 - 4x upscaling	DCLS
Blind Super-Resolution	Set5 - 2x upscaling	DCLS
Blind Super-Resolution	Set5 - 3x upscaling	DCLS
Compressive Sensing	Set5	LapCSNet