中文
相关论文

相关论文: FATE: Full-head Gaussian Avatar with Textural Edit…

200 篇论文

While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness. To fill this gap, we present DipGuava (Disentangled and Personalized…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Jeonghaeng Lee , Seok Keun Choi , Zhixuan Li , Weisi Lin , Sanghoon Lee

Rendering photorealistic head avatars from arbitrary viewpoints is crucial for various applications like virtual reality. Although previous methods based on Neural Radiance Fields (NeRF) can achieve impressive results, they lack fidelity…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Xiaobao Wei , Peng Chen , Ming Lu , Hui Chen , Feng Tian

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

Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries…

Realistic digital avatars require expressive and dynamic hair motion; however, most existing head avatar methods assume rigid hair movement. These methods often fail to disentangle hair from the head, representing it as a simple outer shell…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Berna Kabadayi , Vanessa Sklyarova , Wojciech Zielonka , Justus Thies , Gerard Pons-Moll

Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed…

计算机视觉与模式识别 · 计算机科学 2025-01-09 Han Huang , Yulun Wu , Chao Deng , Ge Gao , Ming Gu , Yu-Shen Liu

In this paper, we explore a reconstruction and reenactment separated framework for 3D Gaussians head, which requires only a single portrait image as input to generate controllable avatar. Specifically, we developed a large-scale one-shot…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Zhiling Ye , Cong Zhou , Xiubao Zhang , Haifeng Shen , Weihong Deng , Quan Lu

Creating high-quality animatable 3D human avatars from a single image remains a significant challenge in computer vision due to the inherent difficulty of reconstructing complete 3D information from a single viewpoint. Current approaches…

计算机视觉与模式识别 · 计算机科学 2025-05-09 Yonwoo Choi

3D Gaussian Splatting (3DGS) has enabled photorealistic and real-time rendering of 3D head avatars. Existing 3DGS-based avatars typically rely on tens of thousands of 3D Gaussian points (Gaussians), with the number of Gaussians fixed after…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Peizhi Yan , Rabab Ward , Qiang Tang , Shan Du

Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DGS-based human avatars has made progress, it still struggles…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Guangan Jiang , Tianzi Zhang , Dong Li , Zhenjun Zhao , Haoang Li , Mingrui Li , Hongyu Wang

Recent advances in generalizable 3D Gaussian Splatting have demonstrated promising results in real-time high-fidelity rendering without per-scene optimization, yet existing approaches still struggle to handle unfamiliar visual content…

计算机视觉与模式识别 · 计算机科学 2025-05-22 Yifan Liu , Keyu Fan , Weihao Yu , Chenxin Li , Hao Lu , Yixuan Yuan

We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day(OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1)…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Dianbing Xi , Guoyuan An , Jingsen Zhu , Zhijian Liu , Yuan Liu , Ruiyuan Zhang , Jiayuan Lu , Yuchi Huo , Rui Wang

Reconstructing dynamic humans interacting with real-world environments from monocular videos is an important and challenging task. Despite considerable progress in 4D neural rendering, existing approaches either model dynamic scenes…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Wenqing Wang , Haosen Yang , Josef Kittler , Xiatian Zhu

We propose OMG-Avatar, a novel One-shot method that leverages a Multi-LOD (Level-of-Detail) Gaussian representation for animatable 3D head reconstruction from a single image in 0.2s. Our method enables LOD head avatar modeling using a…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Jianqiang Ren , Lin Liu , Steven Hoi

Photorealistic and animatable human avatars are a key enabler for virtual/augmented reality, telepresence, and digital entertainment. While recent advances in 3D Gaussian Splatting (3DGS) have greatly improved rendering quality and…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Cheng Peng , Jingxiang Sun , Yushuo Chen , Zhaoqi Su , Zhuo Su , Yebin Liu

In this work, we present a multimodal solution to the problem of 4D face reconstruction from monocular videos. 3D face reconstruction from 2D images is an under-constrained problem due to the ambiguity of depth. State-of-the-art methods try…

计算机视觉与模式识别 · 计算机科学 2023-05-15 Aggelina Chatziagapi , Dimitris Samaras

Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interest in…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Yeheng Zong , Pou-Chun Kung , Yike Pan , Seth Isaacson , Yizhou Chen , Ram Vasudevan , Katherine A. Skinner

We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multi-view generation, 3D Gaussian lifting, and pose-aware UV-space mapping of 3D…

图形学 · 计算机科学 2025-11-18 Marcel C. Bühler , Ye Yuan , Xueting Li , Yangyi Huang , Koki Nagano , Umar Iqbal

A photorealistic and controllable 3D caricaturization framework for faces is introduced. We start with an intrinsic Gaussian curvature-based surface exaggeration technique, which, when coupled with texture, tends to produce over-smoothed…

图形学 · 计算机科学 2026-01-08 Eldad Matmon , Amit Bracha , Noam Rotstein , Ron Kimmel

We present PEGASUS, a method for constructing a personalized generative 3D face avatar from monocular video sources. Our generative 3D avatar enables disentangled controls to selectively alter the facial attributes (e.g., hair or nose)…

计算机视觉与模式识别 · 计算机科学 2024-04-03 Hyunsoo Cha , Byungjun Kim , Hanbyul Joo