AHS: Adaptive Head Synthesis via Synthetic Data Augmentations

• URL: http://arxiv.org/abs/2604.15857v1
• Date: Fri, 17 Apr 2026 09:05:40 GMT
• Title: AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
• Abstract summary: We propose Adaptive Head Synthesis (AHS) to handle full upper-body images with varied head poses and expressions.<n>AHS incorporates a novel head reenacted synthetic data augmentation strategy to overcome self-supervised training constraints.<n>It achieves superior performance in challenging real-world scenarios, producing visually coherent results.
• Score: 39.85130610686079
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Controllable and Expressive One-Shot Video Head Swapping [22.260212663609497]
  We propose a novel diffusion-based multi-condition controllable framework for video head swapping.<n>Our method seamlessly transplants a human head from a static image into a dynamic video, while preserving the original body and background of target video.<n> Experimental results demonstrate that our method excels in seamless background integration while preserving the identity of the source portrait.
  arXiv  Detail & Related papers  (2025-06-20T09:01:17Z)
• Zero-Shot Head Swapping in Real-World Scenarios [30.493743596793212]
  We propose a novel head swapping method, HID, that is robust to images including the full head and the upper body.<n>For automatic mask generation, we introduce the IOMask, which enables seamless blending of the head and body.<n>Our experiments demonstrate that the proposed approach achieves state-of-the-art performance in head swapping.
  arXiv  Detail & Related papers  (2025-03-02T11:44:23Z)
• GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations [54.94362657501809]
  We propose a new method to generate highly dynamic and deformable human head avatars from multi-view imagery in real-time. At the core of our method is a hierarchical representation of head models that allows to capture the complex dynamics of facial expressions and head movements. We train this coarse-to-fine facial avatar model along with the head pose as a learnable parameter in an end-to-end framework.
  arXiv  Detail & Related papers  (2024-09-18T13:05:43Z)
• ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving [64.90148669690228]
  ConsistentID is an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts.<n>We present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets.
  arXiv  Detail & Related papers  (2024-04-25T17:23:43Z)
• eMotion-GAN: A Motion-based GAN for Photorealistic and Facial Expression Preserving Frontal View Synthesis [3.2498796510544636]
  We present eMotion-GAN, a novel deep learning approach designed for frontal view synthesis. Considering the motion induced by head variation as noise and the motion induced by facial expression as the relevant information, our model is trained to filter out the noisy motion. The filtered motion is then mapped onto a neutral frontal face to generate the corresponding expressive frontal face.
  arXiv  Detail & Related papers  (2024-04-15T17:08:53Z)
• FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping [62.38898610210771]
  We present a new single-stage method for subject face swapping and identity transfer, named FaceDancer. We have two major contributions: Adaptive Feature Fusion Attention (AFFA) and Interpreted Feature Similarity Regularization (IFSR)
  arXiv  Detail & Related papers  (2022-10-19T11:31:38Z)
• CIAO! A Contrastive Adaptation Mechanism for Non-Universal Facial Expression Recognition [80.07590100872548]
  We propose Contrastive Inhibitory Adaptati On (CIAO), a mechanism that adapts the last layer of facial encoders to depict specific affective characteristics on different datasets. CIAO presents an improvement in facial expression recognition performance over six different datasets with very unique affective representations.
  arXiv  Detail & Related papers  (2022-08-10T15:46:05Z)
• HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment [63.333407973913374]
  "Face Renovation"(FR) is a semantic-guided generation problem. "HiFaceGAN" is a multi-stage framework containing several nested CSR units. experiments on both synthetic and real face images have verified the superior performance of HiFaceGAN.
  arXiv  Detail & Related papers  (2020-05-11T11:33:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.