# yinboc/liif

Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)

Repository: https://github.com/yinboc/liif
Canonical: https://ross.abutalabs.com/products/liif
Homepage: https://yinboc.github.io/liif/
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: machine-learning, super-resolution, pytorch, implicit-neural-representation
Last push: 2021-08-21T17:43:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2086, "days_push": 1838, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1388, forks 159 (observed 2026-08-28T04:04:35.298160+00:00)

## What it is
LIIF is the official PyTorch implementation of the CVPR 2021 paper 'Learning Continuous Image Representation with Local Implicit Image Function'. It represents images as continuous functions of coordinates, enabling rendering at arbitrary resolutions including extrapolation far beyond training scales.

## Use cases
- upscale images to arbitrary resolutions with a neural network
- super-resolution beyond 30x training scale
- learn continuous implicit representations of 2D images
- reproduce CVPR 2021 LIIF experiments on DIV2K and benchmarks
- train size-varied ground-truth super-resolution models

## When to choose
- you need resolution-free image upscaling or arbitrary-scale super-resolution
- you want to experiment with implicit neural representations for images
- you need the reference implementation for research citation

## When to avoid
- you need a production-ready image upscaler with active maintenance
- you lack a GPU or PyTorch environment
- you need general image editing beyond super-resolution

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, computer-vision, image-processing
- platform: python
- tags: super-resolution, implicit-neural-representation, pytorch, arbitrary-resolution, research-code, cvpr-2021, gpu

## Member repositories
- yinboc/liif (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.298160+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:48.015819+00:00, confidence not recorded.
  - readme: https://github.com/yinboc/liif (fetched 2026-08-28T04:04:35.298160+00:00, sha c3152c557de2)
  - homepage: https://yinboc.github.io/liif/ (fetched 2026-08-29T11:55:08.762537+00:00, sha 7d4a978eb320)
- Data as of 2026-08-30T08:39:29.467469+00:00.