MétaCan
Menu
Back to cohort
Record W4412081546 · doi:10.1109/tcsvt.2025.3586442

3DPortraitGAN: Learning One-Quarter Headshot 3D GANs From a Single-View Portrait Dataset With Diverse Body Poses

2025· article· en· W4412081546 on OpenAlexaboutno aff
Yiqian Wu, Yue Shang-Guan, Hongbo Fu, Xiaogang Jin

Bibliographic record

VenueIEEE Transactions on Circuits and Systems for Video Technology · 2025
Typearticle
Languageen
FieldComputer Science
TopicHuman Pose and Action Recognition
Canadian institutionsnot available
Fundersnot available
KeywordsComputer scienceQuarter (Canadian coin)PortraitArtificial intelligenceComputer visionPattern recognition (psychology)GeographyVisual artsArt

Abstract

fetched live from OpenAlex

3D-aware face generators are typically trained on 2D real-life face image datasets that primarily consist of near-frontal face data. Due to data limitations, these generators cannot generate <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">one-quarter headshot</i> 3D portraits with head, neck, and shoulder geometry, which is crucial for applications like talking heads. Two reasons account for this issue: First, existing facial recognition methods struggle with extracting facial data captured from large camera angles or back views. Second, it is challenging to learn a distribution of 3D portraits covering the one-quarter headshot region from single-view data due to significant geometric deformation caused by diverse body poses. To this end, we first create the dataset <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">360°-Portrait-HQ</i> (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">360°PHQ</i> for short) which consists of high-quality single-view real portraits annotated with a variety of camera parameters (the yaw angles span the entire 360° range) and body poses. We then propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3DPortraitGAN</i>, the first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">360</i>°PHQ dataset with body pose self-learning. Our model can generate view-consistent portrait images from all camera angles with a canonical one-quarter headshot 3D representation. Our experiments show that the proposed framework can accurately predict portrait body poses and generate view-consistent, realistic portrait images with complete geometry from all camera angles.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.977
Threshold uncertainty score0.954

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.027
GPT teacher head0.251
Teacher spread0.224 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Circuits and Systems for Video TechnologySame topicHuman Pose and Action RecognitionFrench-language works237,207