# wywu/LAB

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Repository: https://github.com/wywu/LAB
Canonical: https://ross.abutalabs.com/products/wywu-lab
Homepage: https://wywu.github.io/projects/LAB/LAB.html
Language: C++
License: NOASSERTION
License Family: other
Topics: face-alignment, facial-landmarks, cvpr2018, adversarial-learning
Last push: 2019-10-07T09:45:30+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": 3037, "days_push": 2522, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1019, forks 266 (observed 2026-08-28T04:03:15.100773+00:00)

## What it is
Official C++/Caffe implementation of the CVPR 2018 paper 'Look at Boundary: A Boundary-Aware Face Alignment Algorithm', which localizes facial landmarks via boundary lines. It also introduces the WFLW dataset with 10,000 faces and 98 annotated landmarks.

## Use cases
- detect facial landmarks in images
- align faces for face recognition pipelines
- benchmark face alignment on 300-W, COFW, AFLW, and WFLW
- train a boundary-aware landmark model
- download and use the WFLW dataset for research

## When to choose
- you need state-of-the-art facial landmark localization robust to pose, occlusion, and expression
- you want the WFLW benchmark dataset for face alignment research
- you are reproducing or building on the CVPR 2018 LAB paper

## When to avoid
- you need a maintained production library with active support
- you want a PyTorch or TensorFlow implementation rather than modified Caffe
- you need Windows or macOS support - it targets Linux only

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence
- platform: python, cpp
- tags: face-alignment, facial-landmarks, cvpr2018, caffe, adversarial-learning, wflw-dataset, research-code, linux, gpu

## Member repositories
- wywu/LAB (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:15.100773+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 2026-08-30T07:09:25.026335+00:00, confidence not recorded.
  - readme: https://github.com/wywu/LAB (fetched 2026-08-28T04:03:15.100773+00:00, sha 5324913418f5)
  - homepage: https://wywu.github.io/projects/LAB/LAB.html (fetched 2026-08-29T13:09:33.261314+00:00, sha 124875194bee)
- Data as of 2026-08-30T08:39:29.467469+00:00.