Papers
arxiv:2604.15857

AHS: Adaptive Head Synthesis via Synthetic Data Augmentations

Published on Apr 17
Authors:
,
,
,
,
,
,

Abstract

Adaptive Head Synthesis enables realistic portrait manipulation by handling full upper-body images with diverse head poses and expressions through self-supervised learning with synthetic data augmentation.

AI-generated summary

Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping, where one's head is seamlessly integrated with another's body. However, current approaches predominantly rely on face-centered cropped data with limited view angles, significantly restricting their real-world applicability. They struggle with diverse head expressions, varying hairstyles, and natural blending beyond facial regions. To address these limitations, we propose Adaptive Head Synthesis (AHS), which effectively handles full upper-body images with varied head poses and expressions. AHS incorporates a novel head reenacted synthetic data augmentation strategy to overcome self-supervised training constraints, enhancing generalization across diverse facial expressions and orientations without requiring paired training data. Comprehensive experiments demonstrate that AHS achieves superior performance in challenging real-world scenarios, producing visually coherent results that preserve identity and expression fidelity across various head orientations and hairstyles. Notably, AHS shows exceptional robustness in maintaining facial identity while drastic expression changes and faithfully preserving accessories while significant head pose variations.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.15857
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2604.15857 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.15857 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.