NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results
It addresses the problem of HDR reconstruction for computer vision researchers, but is incremental as it focuses on benchmarking existing methods in a new challenge.
The paper reviews a challenge on high-dynamic range imaging that tackled estimating HDR images from low-dynamic range inputs, with results showing top methods achieving PSNR scores up to 43.2 dB in Track 1 and 48.1 dB in Track 2.
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.