LPIPS (Learned Perceptual Image Patch Similarity)
Source: https://github.com/richzhang/perceptualsimilarity
Structured fields
{
"archived": false,
"revision": {
"ref": "master",
"pinned": false
},
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "BSD-2 implementation of LPIPS, the standard learned full-reference perceptual distance (pip install lpips); used to compare a frame with a reference, for consistency checks and image-restoration evaluation.",
"source_type": "repository",
"availability": "available",
"source_owner": "Richard Zhang et al.",
"next_check_at": "2026-11-16T00:00:00.000Z",
"known_limitations": [
"Full-reference only; needs a ground-truth image."
],
"upstream_updated_at": "2024-07-02T17:30:14.000Z"
}Evidence claims
- [sourced_fact] README: Perceptual Similarity Metric and Dataset from 'The Unreasonable Effectiveness of Deep Features as a Perceptual Metric' (CVPR 2018); install with pip install lpips. · locator: README intro source
- [sourced_fact] Repo metadata: BSD-2-Clause, not archived, last push 2024-07-02. · locator: GitHub API fields source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | BSD-2-Clause | permitted | permitted | permitted | unknown | BSD-2-Clause; backbone network weights (AlexNet, VGG) carry their own terms. |