NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results

TL;DR

This paper reviews the NTIRE 2021 HDR imaging challenge, introducing a new dataset, various methods, and their results for reconstructing high-dynamic range images from low-dynamic range inputs under different conditions.

Contribution

It presents the first HDR imaging challenge with a new dataset, multiple tracks, and evaluation protocols, advancing benchmarking and research in HDR reconstruction.

Findings

Multiple methods evaluated for HDR reconstruction.

Best methods achieved high PSNR scores.

The challenge established a new benchmark for HDR imaging.

Abstract

This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021. This manuscript focuses on the newly introduced dataset, the proposed methods and their results. The challenge aims at estimating a HDR image from one or multiple respective low-dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed by two tracks: In Track 1 only a single LDR image is provided as input, whereas in Track 2 three differently-exposed LDR images with inter-frame motion are available. In both tracks, the ultimate goal is to achieve the best objective HDR reconstruction in terms of PSNR with respect to a ground-truth image, evaluated both directly and with a canonical tonemapping operation.