3D Morphable Face Models -- Past, Present and Future

Adam Kortylewski; Ayush Tewari; Bernhard Egger; Christian Theobalt; Florian Bernard; Michael Zollhoefer; Sami Romdhani; Stefanie Wuhrer; Thabo Beeler; Thomas Vetter

3D Morphable Face Models -- Past, Present and Future

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1909.01815 v2 pith:M3QM2WRP submitted 2019-09-03 cs.CV cs.GRcs.LG

Bernhard Egger , William A. P. Smith , Ayush Tewari , Stefanie Wuhrer , Michael Zollhoefer , Thabo Beeler , Florian Bernard , Timo Bolkart

show 5 more authors

Adam Kortylewski Sami Romdhani Christian Theobalt Volker Blanz Thomas Vetter

This is my paper · ORCID

classification cs.CVcs.GRcs.LG

keywords futuremodelschallengesfaceimagemorphableresearchactive

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Modelship Attribution: Tracing Multi-Stage Manipulations Across Generative Models
cs.CV 2025-06 conditional novelty 6.0 of 10

Modelship Attribution is defined as a new task with an 83,700-image dataset built from three face-swap models, and a transformer, MAT, that predicts the editing model sequence with 76.01% strict-match accuracy.

Pith tools