RESIDE

A new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE). RESIDE highlights diverse data sources and image contents, and is divided into five subsets, each serving different training or evaluation purposes.

Source: RESIDE

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Dehazing	SOTS Indoor	MixDehazeNet
Image Dehazing	SOTS Outdoor	ChaIR
Image Dehazing	RESIDE	LCA-Net
Single Image Haze Removal	RESIDE	DCP
Single Image Dehazing	RESIDE	Lower Bound on Transmission using Non-Linear Bounding Function in Single Image Dehazing