3DRealHead: Few-Shot Detailed Head Avatar

• URL: http://arxiv.org/abs/2604.13171v1
• Date: Tue, 14 Apr 2026 18:00:06 GMT
• Title: 3DRealHead: Few-Shot Detailed Head Avatar
• Abstract summary: We introduce 3DRealHead, a few-shot head avatar reconstruction method with a novel expression control signal.<n>The subject can take a few pictures of themselves, recover a 3D head avatar and drive it with a consumer-level webcam.<n>For animating the avatar, the U-Net is conditioned on 3DMM-based facial expression signals, as well as features of the mouth region extracted from the driving video.
• Score: 37.50886855423571
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The human face is central to communication. For immersive applications, the digital presence of a person should mirror the physical reality, capturing the users idiosyncrasies and detailed facial expressions. However, current 3D head avatar methods often struggle to faithfully reproduce the identity and facial expressions, despite having multi-view data or learned priors. Learning priors that capture the diversity of human appearances, especially, for regions with highly person-specific features, like the mouth and teeth region is challenging as the underlying training data is limited. In addition, many of the avatar methods are purely relying on 3D morphable model-based expression control which strongly limits expressivity. To address these challenges, we are introducing 3DRealHead, a few-shot head avatar reconstruction method with a novel expression control signal that is extracted from a monocular video stream of the subject. Specifically, the subject can take a few pictures of themselves, recover a 3D head avatar and drive it with a consumer-level webcam. The avatar reconstruction is enabled via a novel few-shot inversion process of a 3D human head prior which is represented as a Style U-Net that emits 3D Gaussian primitives which can be rendered under novel views. The prior is learned on the NeRSemble dataset. For animating the avatar, the U-Net is conditioned on 3DMM-based facial expression signals, as well as features of the mouth region extracted from the driving video. These additional mouth features allow us to recover facial expressions that cannot be represented by the 3DMM leading to a higher expressivity and closer resemblance to the physical reality.

Related papers

• Multi-View Face and Gesture Animation with Dynamic Gaussians [19.248725316098465]
  We propose MVFGA, a novel multi-view-consistent pipeline for generating realistic upper-body avatars.<n>Our approach models the face and hands separately and fuses them with a parametric upper-body mesh model.<n>We then splat 3D Gaussians onto the obtained mesh, enabling high-quality photorealistic rendering of dynamic avatars.
  arXiv  Detail & Related papers  (2026-08-05T11:43:21Z)
• Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars [60.0866477932976]
  We present Avat3r, which regresses a high-quality and animatable 3D head avatar from just a few input images.<n>We make Large Reconstruction Models animatable and learn a powerful prior over 3D human heads from a large multi-view video dataset.<n>We increase robustness by feeding input images with different expressions to our model during training, enabling the reconstruction of 3D head avatars from inconsistent inputs.
  arXiv  Detail & Related papers  (2025-02-27T16:00:11Z)
• 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)
• DEGAS: Detailed Expressions on Full-Body Gaussian Avatars [13.683836322899953]
  We present DEGAS, the first 3D Gaussian Splatting (3DGS)-based modeling method for full-body avatars with rich facial expressions.<n>We propose to adopt the expression latent space trained solely on 2D portrait images, bridging the gap between 2D talking faces and 3D avatars.
  arXiv  Detail & Related papers  (2024-08-20T06:52:03Z)
• Expressive Whole-Body 3D Gaussian Avatar [34.3179424934446]
  We present ExAvatar, an expressive whole-body 3D human avatar learned from a short monocular video. The main challenges are 1) a limited diversity of facial expressions and poses in the video and 2) the absence of 3D observations, such as 3D scans and RGBD images.
  arXiv  Detail & Related papers  (2024-07-31T15:29:13Z)
• GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar [48.21353924040671]
  We propose to learn person-specific animatable avatars from images without assuming to have access to precise facial expression tracking. We learn a mapping from 3DMM facial expression parameters to the latent space of the generative model. With this scheme, we decouple 3D appearance reconstruction and animation control to achieve high fidelity in image synthesis.
  arXiv  Detail & Related papers  (2023-11-22T19:13:00Z)
• Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Models [107.84324544272481]
  The ability to generate diverse 3D articulated head avatars is vital to a plethora of applications, including augmented reality, cinematography, and education. Recent work on text-guided 3D object generation has shown great promise in addressing these needs. We show that our diffusion-based articulated head avatars outperform state-of-the-art approaches for this task.
  arXiv  Detail & Related papers  (2023-07-10T19:15:32Z)
• HeadSculpt: Crafting 3D Head Avatars with Text [143.14548696613886]
  We introduce a versatile pipeline dubbed HeadSculpt for crafting 3D head avatars from textual prompts. We first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding. We propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique.
  arXiv  Detail & Related papers  (2023-06-05T16:53:58Z)

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.