Advanced

FLIP: A Difference Evaluator for Alternating Images

Andersson, Pontus LU ; Akenine-Möller, Tomas LU ; Nilsson, Jim ; Åström, Kalle LU ; Oskarsson, Magnus LU and Fairchild, Mark (2020) In Proceedings of the ACM in Computer Graphics and Interactive Techniques 3(2).
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Proceedings of the ACM in Computer Graphics and Interactive Techniques
volume
3
issue
2
article number
15
pages
23 pages
ISSN
2577-6193
project
Spatiotemporal Consistency in Rendering and Deep Learning
language
English
LU publication?
yes
id
397ced35-879a-43a6-a225-ce31b0e984a2
alternative location
https://research.nvidia.com/sites/default/files/node/3260/FLIP_Paper.pdf
https://dl.acm.org/doi/10.1145/3406183
date added to LUP
2020-08-31 11:48:42
date last changed
2020-09-18 08:32:13
@article{397ced35-879a-43a6-a225-ce31b0e984a2,
  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       = {Andersson, Pontus and Akenine-Möller, Tomas and Nilsson, Jim and Åström, Kalle and Oskarsson, Magnus and Fairchild, Mark},
  issn         = {2577-6193},
  language     = {eng},
  number       = {2},
  series       = {Proceedings of the ACM in Computer Graphics and Interactive Techniques},
  title        = {FLIP: A Difference Evaluator for Alternating Images},
  url          = {https://research.nvidia.com/sites/default/files/node/3260/FLIP_Paper.pdf},
  volume       = {3},
  year         = {2020},
}