Detecting and Correcting Perceptual Artifacts in Synthetic Face Images

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00377158" target="_blank" >RIV/68407700:21230/24:00377158 - isvavai.cz</a>

Result on the web

<a href="https://cvww2024.sdrv.si/wp-content/uploads/sites/5/2024/02/CVWW2024_Proceedings.pdf" target="_blank" >https://cvww2024.sdrv.si/wp-content/uploads/sites/5/2024/02/CVWW2024_Proceedings.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Detecting and Correcting Perceptual Artifacts in Synthetic Face Images

Original language description

We propose a method for detecting and automatically correcting perceptual artifacts on synthetic face images. Recent generative models, such as diffusion models, can produce photorealistic images. However, these models often generate visual defects on the faces of people, especially at low resolutions, which impairs the quality of the images. We use a face detector and a binary classifier to identify perceptual artifacts. The classifier was trained on our dataset of manually annotated synthetic face images generated by a diffusion model, half of which contain perceptual artifacts. We compare our method with several baselines and show that it achieves superior accuracy of 93% on an independent test set. In addition, we propose a simple mechanism for automatically correcting the distorted faces using inpainting. For each face with artifact response, we generate several replacement candidates by inpainting and choose the best one by the lowest artifact score. The best candidate is then back-projected into to the image. Inpainting ensures a seamless connection between the corrected face and the original image. Our method improves the realism and quality of synthetic images.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 27th Computer Vision Winter Workshop

ISBN

978-961-96564-0-2

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

38-46

Publisher name

Slovenian Pattern Recognition Society

Place of publication

Ljubljana

Event location

Terme Olimia

Event date

Feb 14, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—