Skip to main navigation Skip to search Skip to main content

Ig3D: Integrating 3D Face Representations in Facial Expression Inference

  • SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Reconstructing 3D faces with facial geometry from single images has allowed for major advances in animation, generative models, and virtual reality. However, this ability to represent faces with their 3D features is not as fully explored by the facial expression inference (FEI) community. This study therefore aims to investigate the impacts of integrating such 3D representations into the FEI task, specifically for facial expression classification and face-based valence-arousal (VA) estimation. To achieve this, we first evaluate the performance of two 3D face representations (both based on the 3D morphable model, FLAME) for the FEI tasks. We further explore two fusion architectures, intermediate fusion, and late fusion, for integrating the 3D face representations with existing 2D inference frameworks. To evaluate the proposed architecture, we extract the corresponding 3D representations and perform extensive experiments on the AffectNet and RAF-DB datasets. The experimental results show that our method outperforms the state-of-the-art in AffectNet VA estimation and RAF-DB classification tasks. Furthermore, our method can serve as a complement to other existing methods to boost performance in many emotion inference tasks.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2024 Workshops , Proceedings
EditorsAlessio Del Bue, Cristian Canton, Jordi Pont-Tuset, Tatiana Tommasi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages404-421
Number of pages18
ISBN (Print)9783031915802
DOIs
StatePublished - 2025
Event18th European Conference on Computer Vision, ECCV 2024 - Milan, Italy
Duration: Sep 29 2024Oct 4 2024

Publication series

NameLecture Notes in Computer Science
Volume15637 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference18th European Conference on Computer Vision, ECCV 2024
Country/TerritoryItaly
CityMilan
Period09/29/2410/4/24

Keywords

  • 3D Face Representations
  • Facial Expression Inference
  • Intermediate and Late Fusion

Fingerprint

Dive into the research topics of 'Ig3D: Integrating 3D Face Representations in Facial Expression Inference'. Together they form a unique fingerprint.

Cite this