Images

CBSD68 (Color BSD68)

Introduced by David R. Martin et al. in A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics

Color BSD68 dataset for image denoising benchmarks is part of The Berkeley Segmentation Dataset and Benchmark. It is used for measuring image denoising algorithms performance. It contains 68 images.

Source: https://github.com/clausmichele/CBSD68-dataset

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Color Image Denoising	CBSD68 sigma50	IPT
Color Image Denoising	CBSD68 sigma15	ADL
Color Image Denoising	CBSD68 sigma25	KBNet
Color Image Denoising	CBSD68 sigma35	ADL
Color Image Denoising	CBSD68 sigma75	HyperRes
Color Image Denoising	CBSD68 sigma5	CBUIFD75
Color Image Denoising	CBSD68 sigma55	HyperRes
Color Image Denoising	CBSD68 sigma65	HyperRes
Color Image Denoising	CBSD68 sigma45	HyperRes
Color Image Denoising	CBSD68 sigma10	CBUIFD75
Image Compressed Sensing	CBSD68	CASNet
Color Image Denoising	CBSD68 sigma20	CBUIFD75
Color Image Denoising	CBSD68 sigma30	CBUIFD75
Color Image Denoising	CBSD68 sigma40	CBUIFD75
Color Image Denoising	CBSD68 sigma60	CBUIFD75
Color Image Denoising	CBSD68 sigma70	CBUIFD75