HDR-VDP-2: a calibrated visual metric for visibility and quality predictions in all luminance conditions

By Rafał K. Mantiuk, Kil Joong Kim, Allan G. Rempel, Wolfgang Heidrich. 2011

978 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018, background): “called full-reference image quality assessment (FR-IQA), has been a longstanding goal in the community, and there have been numerous perceptually motivated distance metrics proposed, such as SSIM [53], MSSIM [55], FSIM [57], and HDR-VDP [32].”
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (2023, positive): “Patch-based metrics, including SSIM [88], FSIM [92], and HDR-VDP-2 [55] tackle this issue and are widely used in applications involving photometric distortions such as image quality assessment.”
A no-reference metric for evaluating the quality of motion deblurring (2013, methodology): “Commonly used fullreference metrics include PSNR [Teo and Heeger 1994], multiscale SSIM [Wang et al. 2004], VIF [Sheikh and Bovik 2006], HDR-VDP-2 [Mantiuk et al. 2011], and a linear combination of them [Masia et al. 2012].”
Deep reverse tone mapping (2017, methodology): “As an evaluation metric, we used HDR-VDP-2 [Mantiuk et al. 2011], which can compute visual difference based on human perception rather than a mathematical differences such as root-mean-square-error between two HDR images.”
Deep High Dynamic Range Imaging with Large Foreground Motions (2017, methodology): “While [14] results in slightly higher PSNR scores, our methods result in comparable SSIM scores and slightly higher HDR-VDP-2 scores.”
E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles (2019, background): “Perceptually motivated image similarity metrics have a long history, with well-known challenges due to dependence on context and high-level image structure [27, 28, 20].”