https://github.com/abhijay9/shifttolerant-lpips
[ECCV 2022] We investigated a broad range of neural network elements and developed a robust perceptual similarity metric. Our shift-tolerant perceptual similarity metric (ST-LPIPS) is consistent with human perception and is less susceptible to imperceptible misalignments between two images than existing metrics.
https://github.com/abhijay9/shifttolerant-lpips
full-reference-image-quality-assessment full-reference-iqa image-quality-assessment iqa ml-robustness perceptual-similarity
Last synced: 2 months ago
JSON representation
[ECCV 2022] We investigated a broad range of neural network elements and developed a robust perceptual similarity metric. Our shift-tolerant perceptual similarity metric (ST-LPIPS) is consistent with human perception and is less susceptible to imperceptible misalignments between two images than existing metrics.
- Host: GitHub
- URL: https://github.com/abhijay9/shifttolerant-lpips
- Owner: abhijay9
- License: bsd-2-clause
- Created: 2022-08-10T05:21:01.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2024-05-21T23:35:28.000Z (about 2 years ago)
- Last Synced: 2025-12-15T18:42:06.274Z (6 months ago)
- Topics: full-reference-image-quality-assessment, full-reference-iqa, image-quality-assessment, iqa, ml-robustness, perceptual-similarity
- Language: Python
- Homepage:
- Size: 240 MB
- Stars: 41
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE