跳至内容
  • 首页
  • 资讯
  • 资源下载
  • 行业方案
  • Job招聘
  • Paper论文
  • Patent专利
  • 映维会员
  • 导航收录
  • 合作
  • 关于
  • 微信群
  • All
  • XR
  • CV
  • CG
  • HCI
  • Video
  • Optics
  • Perception
  • Reconstruction

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

小编 广东客   |   分类:CV   |   发布日期 2025年3月4日

Note: We don't have the ability to review paper

PubDate: Feb 2025

Teams:Technical University of Munich,Meta Reality Labs

Writers:Tobias Kirschstein, Javier Romero, Artem Sevastopolsky, Matthias Nießner, Shunsuke Saito

PDF:Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

Abstract

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings.

To address this shortcoming, we present Avat3r, which regresses a high-quality and animatable 3D head avatar from just a few input images, vastly reducing compute requirements during inference. More specifically, we make Large Reconstruction Models animatable and learn a powerful prior over 3D human heads from a large multi-view video dataset. For better 3D head reconstructions, we employ position maps from DUSt3R and generalized feature maps from the human foundation model Sapiens. To animate the 3D head, our key discovery is that simple cross-attention to an expression code is already sufficient. Finally, 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, e.g., an imperfect phone capture with accidental movement, or frames from a monocular video.

We compare Avat3r with current state-of-the-art methods for few-input and single-input scenarios, and find that our method has a competitive advantage in both tasks. Finally, we demonstrate the wide applicability of our proposed model, creating 3D head avatars from images of different sources, smartphone captures, single images, and even out-of-domain inputs like antique busts.

本文链接:https://paper.nweon.com/16226

您可能还喜欢...

  • Application and Evaluation of Lighthouse Technology for Precision Motion Capture

    2020年10月26日 映维

  • EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction on Mobile Devices

    2023年11月23日 映维

  • Shape from Sky: Polarimetric Normal Recovery Under The Sky

    2021年06月30日 映维

关注:

RSS 最新AR/VR行业分享

  • 映维日报:光场显示CREAL获蔡司领投890万美元,深圳机场128万招标VR大空间项目 2025年7月11日
  • 《Prison Boss: Prohibition》登陆Meta Quest及SteamVR平台 2025年7月11日
  • Meta发布XR Audio SDK插件支持Wwise空间音频开发 2025年7月11日
  • 杭州"石窟艺术超感沉浸展"以PICO VR/MR技术活化文化遗产 2025年7月11日
  • 南京博物院推出《坤舆万国全图》PICO VR大空间沉浸展 2025年7月11日

RSS 最新AR/VR专利

  • Samsung Patent | Deposition mask, deposition equipment including deposition mask, method of manufacturing display device using deposition equipment, and display device manufactured by method thereof 2025年7月10日
  • Meta Patent | Techniques for avoiding negative audio performance variations in extended-reality devices, and mixed-reality systems and methods of using these techniques 2025年7月10日
  • LG Patent | Light guide member comprising diffraction pattern 2025年7月10日
  • Vuzix Patent | Multiple wavelength range imaging light guide system 2025年7月10日
  • HTC Patent | Head-mounted display device 2025年7月10日

RSS 最新AR/VR行业招聘

  • Microsoft AR/VR Job | High Performance Compute, Director 2025年6月5日
  • Microsoft AR/VR Job | Data Center Technician/ Technicien de Centre de Données 2025年6月3日
  • Microsoft AR/VR Job | Senior Product Designer 2025年5月16日
  • Apple AR/VR Job | AirPlay Audio Engineer 2025年3月27日
  • Apple AR/VR Job | iOS Perception Engineer 2025年3月27日
  • 首页
  • 资讯
  • 资源下载
  • 行业方案
  • Job招聘
  • Paper论文
  • Patent专利
  • 映维会员
  • 导航收录
  • 合作
  • 关于
  • 微信群

联系微信:ovalics

版权所有:广州映维网络有限公司 © 2025

备案许可:粤ICP备17113731号-2

粤公网安备 44011302004835号

友情链接: AR/VR行业导航

读者QQ群:251118691

Quest QQ群:526200310

开发者QQ群:688769630

Paper