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 underor 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.

Laplacian Pyramid Blending is a commonly used method for several seamless image blending tasks. While the method works well for images with comparable intensity levels, it is often unable to produce artifact free images for applications which handle images with large intensity variation such as exposure fusion. This paper proposes a spatially varying Laplacian Pyramid Blending to blend images with large intensity differences. The proposed method dynamically alters the blending levels during the final stage of Pyramid Reconstruction based on the amount of local intensity variation. The proposed algorithm out performs state-of-the-art methods for image blending both qualitatively as well as quantitatively on publicly available High Dynamic Range (HDR) imaging dataset. Qualitative improvements are demonstrated in terms of details, halos and dark halos. For quantitative comparison, the noreference perceptual metric MEF-SSIM was used.

No abstract

No abstract

No abstract