Benchmarking Single-Image Dehazing and Beyond

Abstract

In this paper, we present a comprehensive study and evaluation of existing single image dehazing algorithms, using 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. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on RESIDE shed light on the comparisons and limitations of stateof- the-art dehazing algorithms, and suggest promising future directions.

Keywords

Affiliated Institutions

• Texas A&M University US
• Microsoft Research Asia (China) CN
• Chinese Academy of Sciences CN
• University of Science and Technology of China CN
• Institute of Information Engineering CN
• Cornell University US
• The University of Sydney AU
• Huazhong University of Science and Technology CN

Related Publications