Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Hao, Mallick, Rupayan, Betke, Margrit, Bargal, Sarah Adel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918124344836096
author Yu, Hao
Mallick, Rupayan
Betke, Margrit
Bargal, Sarah Adel
author_facet Yu, Hao
Mallick, Rupayan
Betke, Margrit
Bargal, Sarah Adel
contents Different forms of customized 2D avatars are widely used in gaming applications, virtual communication, education, and content creation. However, existing approaches often fail to capture fine-grained facial expressions and struggle to preserve identity across different expressions. We propose GEN-AFFECT, a novel framework for personalized avatar generation that generates expressive and identity-consistent avatars with a diverse set of facial expressions. Our framework proposes conditioning a multimodal diffusion transformer on an extracted identity-expression representation. This enables identity preservation and representation of a wide range of facial expressions. GEN-AFFECT additionally employs consistent attention at inference for information sharing across the set of generated expressions, enabling the generation process to maintain identity consistency over the array of generated fine-grained expressions. GEN-AFFECT demonstrates superior performance compared to previous state-of-the-art methods on the basis of the accuracy of the generated expressions, the preservation of the identity and the consistency of the target identity across an array of fine-grained facial expressions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09461
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy
Yu, Hao
Mallick, Rupayan
Betke, Margrit
Bargal, Sarah Adel
Computer Vision and Pattern Recognition
Artificial Intelligence
Different forms of customized 2D avatars are widely used in gaming applications, virtual communication, education, and content creation. However, existing approaches often fail to capture fine-grained facial expressions and struggle to preserve identity across different expressions. We propose GEN-AFFECT, a novel framework for personalized avatar generation that generates expressive and identity-consistent avatars with a diverse set of facial expressions. Our framework proposes conditioning a multimodal diffusion transformer on an extracted identity-expression representation. This enables identity preservation and representation of a wide range of facial expressions. GEN-AFFECT additionally employs consistent attention at inference for information sharing across the set of generated expressions, enabling the generation process to maintain identity consistency over the array of generated fine-grained expressions. GEN-AFFECT demonstrates superior performance compared to previous state-of-the-art methods on the basis of the accuracy of the generated expressions, the preservation of the identity and the consistency of the target identity across an array of fine-grained facial expressions.
title Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.09461