Cited by 613Face recognition and analysisFace and Expression RecognitionFace Recognition and Perception

Effective face frontalization in unconstrained images

Hassner, Tal, Harel, Shai, Paz, Eran, Enbar, Roee·2015·2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

“Frontalization” is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos. Recent reports have suggested that this process may substantially boost the performance of face recognition systems. This, by transforming the challenging problem of recognizing faces viewed from unconstrained viewpoints to the easier problem of recognizing faces in constrained, forward facing poses. Previous frontalization methods did this by attempting to approximate 3D facial shapes for each query image. We observe that 3D face shape estimation from unconstrained photos may be a harder problem than frontalization and can potentially introduce facial misalignments. Instead, we explore the simpler approach of using a single, unmodified, 3D surface as an approximation to the shape of all input faces. We show that this leads to a straightforward, efficient and easy to implement method for frontalization. More importantly, it produces aesthetic new frontal views and is surprisingly effective when used for face recognition and gender estimation.

Integrity signals

Registry

Crossref · 10.1109/cvpr.2015.7299058

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • More advanced face frontalization involving approximation of 3D shape is useful when dealing with 3D head pose variation.

    “More advanced face frontalization involving the approximation of 3D shape is useful when dealing with 3D head pose variation [104], [105].”

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Hassner, T., Harel, S., Paz, E., & Enbar, R.
Affiliations
Open University of Israel (IL)
Venue
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2015-06
Pages
4295-4304
ISSN
1063-6919 (ISSN-L)
OpenAlex
W1916406603
Cited by
613
References
41
Citations by year
2026: 3 · 2025: 18 · 2024: 26 · 2023: 40 · 2022: 54 · 2021: 69 · 2020: 74 · 2019: 84 · 2018: 83 · 2017: 85 · 2016: 56 · 2015: 21
FWCI
33.49
Type
conference paper
Language
en
Open access
closed
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Funders
Office of the Director of National Intelligence
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
Keywords
face frontalization, unconstrained face images, face recognition, gender prediction, frontal view

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review