richzhang/PerceptualSimilarity
A PyTorch library implementing LPIPS, a perceptual similarity metric based on deep features for evaluating image quality and similarity.
Not currently ranked — collecting fresh signals.
star history
This repository provides the Learned Perceptual Image Patch Similarity (LPIPS) metric and the Berkeley-Adobe Perceptual Patch Similarity (BAPPS) dataset. The metric measures perceptual similarity between images by comparing deep neural network feature activations rather than pixel-level differences. It can serve as both an evaluation metric and a perceptual loss for optimization tasks like image generation and style transfer. The library offers pretrained backbones (alex, vgg) and integrates with PyTorch.
Frequently asked
- What is richzhang/PerceptualSimilarity?
- A PyTorch library implementing LPIPS, a perceptual similarity metric based on deep features for evaluating image quality and similarity.
- Is PerceptualSimilarity open source?
- Yes — richzhang/PerceptualSimilarity is open source, released under the BSD-2-Clause license.
- What language is PerceptualSimilarity written in?
- richzhang/PerceptualSimilarity is primarily written in Python.
- How popular is PerceptualSimilarity?
- richzhang/PerceptualSimilarity has 4.3k stars on GitHub.
- Where can I find PerceptualSimilarity?
- richzhang/PerceptualSimilarity is on GitHub at https://github.com/richzhang/PerceptualSimilarity.