FLIP: A Difference Evaluator for Alternating Images
| dc.contributor.author | Andersson, Pontus | en_US |
| dc.contributor.author | Nilsson, Jim | en_US |
| dc.contributor.author | Akenine-Möller, Tomas | en_US |
| dc.contributor.author | Oskarsson, Magnus | en_US |
| dc.contributor.author | Åström, Kalle | en_US |
| dc.contributor.author | Fairchild, Mark D. | en_US |
| dc.contributor.editor | Yuksel, Cem and Membarth, Richard and Zordan, Victor | en_US |
| dc.date.accessioned | 2020-10-30T18:18:27Z | |
| dc.date.available | 2020-10-30T18:18:27Z | |
| dc.date.issued | 2020 | |
| dc.description.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. | en_US |
| dc.description.number | 2 | |
| dc.description.sectionheaders | Image-Based Computing | |
| dc.description.seriesinformation | Proceedings of the ACM on Computer Graphics and Interactive Techniques | |
| dc.description.volume | 3 | |
| dc.identifier.doi | 10.1145/3406183 | |
| dc.identifier.issn | 2577-6193 | |
| dc.identifier.uri | https://doi.org/10.1145/3406183 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1145/3406183 | |
| dc.publisher | ACM | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Image processing | |
| dc.subject | Rendering. | |
| dc.subject | image difference | |
| dc.subject | image metric | |
| dc.title | FLIP: A Difference Evaluator for Alternating Images | en_US |