中文
相关论文

相关论文: AvatarMAV: Fast 3D Head Avatar Reconstruction Usin…

200 篇论文

Building 3D animatable head avatars from a single image is an important yet challenging problem. Existing methods generally collapse under large camera pose variations, compromising the realism of 3D avatars. In this work, we propose a new…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Shuling Zhao , Dan Xu

The efficient reconstruction of high-quality and intuitively editable human avatars presents a pressing challenge in the field of computer vision. Recent advancements, such as 3DGS, have demonstrated impressive reconstruction efficiency and…

图形学 · 计算机科学 2025-11-25 Mengtian Li , Shengxiang Yao , Yichen Pan , Haiyao Xiao , Zhongmei Li , Zhifeng Xie , Keyu Chen

3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Jian Shu , Nanjie Yao , Gangjian Zhang , Junlong Ren , Yu Feng , Hao Wang

Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one single scene. Explicit data structures, e.g. voxel features,…

计算机视觉与模式识别 · 计算机科学 2022-09-27 Jiemin Fang , Taoran Yi , Xinggang Wang , Lingxi Xie , Xiaopeng Zhang , Wenyu Liu , Matthias Nießner , Qi Tian

We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on…

计算机视觉与模式识别 · 计算机科学 2022-09-02 Tao Hu , Tao Yu , Zerong Zheng , He Zhang , Yebin Liu , Matthias Zwicker

This paper presents a method that can quickly adapt dynamic 3D avatars to arbitrary text descriptions of novel styles. Among existing approaches for avatar stylization, direct optimization methods can produce excellent results for arbitrary…

计算机视觉与模式识别 · 计算机科学 2023-05-31 Thu Nguyen-Phuoc , Gabriel Schwartz , Yuting Ye , Stephen Lombardi , Lei Xiao

We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views. Our method is based on a dynamic Neural Radiance Field (NeRF) rigged by…

计算机视觉与模式识别 · 计算机科学 2022-08-19 Gusi Te , Xiu Li , Xiao Li , Jinglu Wang , Wei Hu , Yan Lu

High-fidelity reconstruction of 3D human avatars has a wild application in visual reality. In this paper, we introduce FAGhead, a method that enables fully controllable human portraits from monocular videos. We explicit the traditional 3D…

计算机视觉与模式识别 · 计算机科学 2024-07-01 Yixin Xuan , Xinyang Li , Gongxin Yao , Shiwei Zhou , Donghui Sun , Xiaoxin Chen , Yu Pan

Controllability, generalizability and efficiency are the major objectives of constructing face avatars represented by neural implicit field. However, existing methods have not managed to accommodate the three requirements simultaneously.…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Zhiyuan Ma , Xiangyu Zhu , Guojun Qi , Zhen Lei , Lei Zhang

By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity. However, most existing methods only reconstruct a head without the…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Tianhao Wu , Jing Yang , Zhilin Guo , Jingyi Wan , Fangcheng Zhong , Cengiz Oztireli

Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view misalignment, occlusions, and the absence of structural…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Lingteng Qiu , Peihao Li , Heyuan Li , Qi Zuo , Xiaodong Gu , Yuan Dong , Weihao Yuan , Rui Peng , Siyu Zhu , Xiaoguang Han , Guanying Chen , Zilong Dong

Creating high-fidelity 3D human head avatars is crucial for applications in VR/AR, digital human, and film production. Recent advances have leveraged morphable face models to generate animated head avatars from easily accessible data,…

计算机视觉与模式识别 · 计算机科学 2024-10-24 Yuelang Xu , Zhaoqi Su , Qingyao Wu , Yebin Liu

Sparse volumetric reconstruction and rendering via 3D Gaussian splatting have recently enabled animatable 3D head avatars that are rendered under arbitrary viewpoints with impressive photorealism. Today, such photoreal avatars are seen as a…

计算机视觉与模式识别 · 计算机科学 2025-05-12 Gengyan Li , Paulo Gotardo , Timo Bolkart , Stephan Garbin , Kripasindhu Sarkar , Abhimitra Meka , Alexandros Lattas , Thabo Beeler

Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry and expression details. This challenge arises from limited facial representational capacity…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Willem Menu , Erkut Akdag , Pedro Quesado , Yasaman Kashefbahrami , Egor Bondarev

Recent advances in Gaussian Splatting have significantly boosted the reconstruction of head avatars, enabling high-quality facial modeling by representing an 3D avatar as a collection of 3D Gaussians. However, existing methods predominantly…

计算机视觉与模式识别 · 计算机科学 2025-08-29 Shiqi Xin , Xiaolin Zhang , Yanbin Liu , Peng Zhang , Caifeng Shan

We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Jiapeng Tang , Davide Davoli , Tobias Kirschstein , Liam Schoneveld , Matthias Niessner

Constructing drivable and photorealistic 3D head avatars has become a central task in AR/XR, enabling immersive and expressive user experiences. With the emergence of high-fidelity and efficient representations such as 3D Gaussians, recent…

图形学 · 计算机科学 2025-12-25 Jaeseong Lee , Junyeong Ahn , Taewoong Kang , Jaegul Choo

The creation of 3D human avatars from multi-view videos is a significant yet challenging task in computer vision. However, existing techniques rely on high-quality, sharp images as input, which are often impractical to obtain in real-world…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Muyao Niu , Yifan Zhan , Qingtian Zhu , Zhuoxiao Li , Wei Wang , Zhihang Zhong , Xiao Sun , Yinqiang Zheng

Modeling dynamic scenes is important for many applications such as virtual reality and telepresence. Despite achieving unprecedented fidelity for novel view synthesis in dynamic scenes, existing methods based on Neural Radiance Fields…

计算机视觉与模式识别 · 计算机科学 2022-06-07 Jia-Wei Liu , Yan-Pei Cao , Weijia Mao , Wenqiao Zhang , David Junhao Zhang , Jussi Keppo , Ying Shan , Xiaohu Qie , Mike Zheng Shou

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. Existing methods either involve time-consuming optimization for a specific person with multiple images, or they struggle to synthesize…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Xueting Li , Shalini De Mello , Sifei Liu , Koki Nagano , Umar Iqbal , Jan Kautz