{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/4"}],"enrichment":{"capability":"Computes perceptual similarity between image pairs using deep neural network features, returning a scalar distance metric where lower values indicate more similar images.","skillfed_tags":["image-similarity","perceptual-metric","computer-vision"],"use_cases":["Evaluate image generation quality by measuring perceptual distance between generated and reference images","Use as a loss function during training of image-to-image translation or super-resolution models","Compare different image processing algorithms (denoising, deblurring, color correction) against human perception","Benchmark perceptual quality of compressed or distorted images in computer vision pipelines","Optimize image synthesis tasks by backpropagating through the metric to guide model training"],"what_it_does":"LPIPS is a learned perceptual similarity metric that measures how different two images are by comparing their deep neural network feature representations. Rather than using pixel-level differences, it leverages the fact that intermediate activations from pre-trained networks (AlexNet, VGG, or SqueezeNet) correlate well with human perceptual judgments. The package provides three network variants with optional linear calibration layers trained on the Berkeley-Adobe Perceptual Patch Similarity (BAPPS) dataset.\n\nYou use it by instantiating a loss function object with your chosen network, then calling it on pairs of PyTorch tensors (images normalized to [-1, 1] range). It returns a scalar or batch of distances where lower values mean more similar images. The metric can be used for evaluation (comparing generated images to references) or as a differentiable loss function for optimization tasks like image generation, super-resolution, or deblurring.","worth_installing":"Yes, if you need a perceptual image similarity metric for computer vision tasks. The package is stable, has low dependencies, and is widely used (1.2M monthly downloads). However, it is dormant\u2014no active maintenance since 2021\u2014so expect no bug fixes or updates. Install it for evaluation or loss functions in image generation, super-resolution, or quality assessment workflows where perceptual alignment matters more than pixel-level similarity."},"id":"lpips","links":{"html":"https://skillfed.io/packages/lpips","md":"https://skillfed.io/packages/lpips.md","pypi":"https://pypi.org/project/lpips/"},"maintenance":{"status":"dormant"},"meta":{"latest_release":"2021-08-25","license_spdx":null,"license_treatment":"permissive","name":"lpips","python_support":"unspecified","summary":"LPIPS Similarity metric"},"popularity":{"monthly_downloads":1205472,"position":4224,"tier":"top_5000"},"security":{"n_vulnerabilities":0},"version":"0.1.4"}