PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting
- URL: http://arxiv.org/abs/2401.12900v5
- Date: Mon, 24 Jun 2024 02:30:09 GMT
- Title: PSAvatar: A Point-based Shape Model for Real-Time Head Avatar Animation with 3D Gaussian Splatting
- Authors: Zhongyuan Zhao, Zhenyu Bao, Qing Li, Guoping Qiu, Kanglin Liu,
- Abstract summary: PSAvatar is a novel framework for animatable head avatar creation.
It employs 3D Gaussian for fine detail representation and high fidelity rendering.
We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time.
- Score: 17.78639236586134
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Despite much progress, achieving real-time high-fidelity head avatar animation is still difficult and existing methods have to trade-off between speed and quality. 3DMM based methods often fail to model non-facial structures such as eyeglasses and hairstyles, while neural implicit models suffer from deformation inflexibility and rendering inefficiency. Although 3D Gaussian has been demonstrated to possess promising capability for geometry representation and radiance field reconstruction, applying 3D Gaussian in head avatar creation remains a major challenge since it is difficult for 3D Gaussian to model the head shape variations caused by changing poses and expressions. In this paper, we introduce PSAvatar, a novel framework for animatable head avatar creation that utilizes discrete geometric primitive to create a parametric morphable shape model and employs 3D Gaussian for fine detail representation and high fidelity rendering. The parametric morphable shape model is a Point-based Morphable Shape Model (PMSM) which uses points instead of meshes for 3D representation to achieve enhanced representation flexibility. The PMSM first converts the FLAME mesh to points by sampling on the surfaces as well as off the meshes to enable the reconstruction of not only surface-like structures but also complex geometries such as eyeglasses and hairstyles. By aligning these points with the head shape in an analysis-by-synthesis manner, the PMSM makes it possible to utilize 3D Gaussian for fine detail representation and appearance modeling, thus enabling the creation of high-fidelity avatars. We show that PSAvatar can reconstruct high-fidelity head avatars of a variety of subjects and the avatars can be animated in real-time ($\ge$ 25 fps at a resolution of 512 $\times$ 512 ).
Related papers
- PrismAvatar: Real-time animated 3D neural head avatars on edge devices [2.446672595462589]
We present PrismAvatar, a 3D head avatar model which is designed specifically to enable real-time animation and rendering on resource-constrained edge devices.
In addition to running at 60 fps with low memory usage on mobile devices, we find that our trained models have comparable quality to state-of-the-art 3D avatar models on desktop devices.
arXiv Detail & Related papers (2025-02-10T20:50:12Z) - Generating Editable Head Avatars with 3D Gaussian GANs [57.51487984425395]
Traditional 3D-aware generative adversarial networks (GANs) achieve photorealistic and view-consistent 3D head synthesis.
We propose a novel approach that enhances the editability and animation control of 3D head avatars by incorporating 3D Gaussian Splatting (3DGS) as an explicit 3D representation.
Our approach delivers high-quality 3D-aware synthesis with state-of-the-art controllability.
arXiv Detail & Related papers (2024-12-26T10:10:03Z) - GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction [47.113910048252805]
High-fidelity 3D human head avatars are crucial for applications in VR/AR, digital human, and film production.
Recent advances have leveraged morphable face models to generate animated head avatars, representing varying identities and expressions.
We introduce 3D Gaussian Parametric Head Model, which employs 3D Gaussians to accurately represent the complexities of the human head.
arXiv Detail & Related papers (2024-07-21T06:03:11Z) - SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded
Gaussian Splatting [26.849406891462557]
We present SplattingAvatar, a hybrid 3D representation of human avatars with Gaussian Splatting embedded on a triangle mesh.
SplattingAvatar renders over 300 FPS on a modern GPU and 30 FPS on a mobile device.
arXiv Detail & Related papers (2024-03-08T06:28:09Z) - HHAvatar: Gaussian Head Avatar with Dynamic Hairs [27.20228210350169]
We proposeAvatar represented by controllable 3D Gaussians for high-fidelity head avatar with dynamic hair modeling.
Our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution.
arXiv Detail & Related papers (2023-12-05T11:01:44Z) - GETAvatar: Generative Textured Meshes for Animatable Human Avatars [69.56959932421057]
We study the problem of 3D-aware full-body human generation, aiming at creating animatable human avatars with high-quality geometries and textures.
We propose GETAvatar, a Generative model that directly generates Explicit Textured 3D rendering for animatable human Avatar.
arXiv Detail & Related papers (2023-10-04T10:30:24Z) - PointAvatar: Deformable Point-based Head Avatars from Videos [103.43941945044294]
PointAvatar is a deformable point-based representation that disentangles the source color into intrinsic albedo and normal-dependent shading.
We show that our method is able to generate animatable 3D avatars using monocular videos from multiple sources.
arXiv Detail & Related papers (2022-12-16T10:05:31Z) - AvatarGen: A 3D Generative Model for Animatable Human Avatars [108.11137221845352]
AvatarGen is an unsupervised generation of 3D-aware clothed humans with various appearances and controllable geometries.
Our method can generate animatable 3D human avatars with high-quality appearance and geometry modeling.
It is competent for many applications, e.g., single-view reconstruction, re-animation, and text-guided synthesis/editing.
arXiv Detail & Related papers (2022-11-26T15:15:45Z) - DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance
Fields for Articulated Avatars [92.37436369781692]
We present DRaCoN, a framework for learning full-body volumetric avatars.
It exploits the advantages of both the 2D and 3D neural rendering techniques.
Experiments on the challenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperforms state-of-the-art methods.
arXiv Detail & Related papers (2022-03-29T17:59:15Z)
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.