FLIP: A Difference Evaluator for Alternating Images

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift


title = "FLIP: A Difference Evaluator for Alternating Images",
abstract = "Image quality measures are becoming increasingly important in the field of computer graphics. For example, there is currently a major focus on generating photorealistic images in real time by combining path tracing with denoising, for which such quality assessment is integral. We present FLIP, which is a difference evaluator with a particular focus on the differences between rendered images and corresponding ground truths. Our algorithm produces a map that approximates the difference perceived by humans when alternating between two images. FLIP is a combination of modified existing building blocks, and the net result is surprisingly powerful. We have compared our work against a wide range of existing image difference algorithms and we have visually inspected over a thousand image pairs that were either retrieved from image databases or generated in-house. We also present results of a user study which indicate that our method performs substantially better, on average, than the other algorithms. To facilitate the use of FLIP, we provide source code in C++, MATLAB, NumPy/SciPy, and PyTorch.",
author = "Pontus Andersson and Tomas Akenine-M{\"o}ller and Jim Nilsson and Kalle {\AA}str{\"o}m and Magnus Oskarsson and Mark Fairchild",
year = "2020",
month = aug,
language = "English",
volume = "3",
journal = "Proceedings of the ACM in Computer Graphics and Interactive Techniques",
issn = "2577-6193",
number = "2",