中文
相关论文

相关论文: Topology-aware Human Avatars with Semantically-gui…

200 篇论文

Real-time rendering of high-fidelity and animatable avatars from monocular videos remains a challenging problem in computer vision and graphics. Over the past few years, the Neural Radiance Field (NeRF) has made significant progress in…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Qipeng Yan , Mingyang Sun , Lihua Zhang

In this paper, we introduce GaussianMotion, a novel human rendering model that generates fully animatable scenes aligned with textual descriptions using Gaussian Splatting. Although existing methods achieve reasonable text-to-3D generation…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Gyumin Shim , Sangmin Lee , Jaegul Choo

Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Ye Yuan , Xueting Li , Yangyi Huang , Shalini De Mello , Koki Nagano , Jan Kautz , Umar Iqbal

Real-time rendering of human head avatars is a cornerstone of many computer graphics applications, such as augmented reality, video games, and films, to name a few. Recent approaches address this challenge with computationally efficient…

计算机视觉与模式识别 · 计算机科学 2024-09-19 Kartik Teotia , Hyeongwoo Kim , Pablo Garrido , Marc Habermann , Mohamed Elgharib , Christian Theobalt

Recent advancements in Gaussian-based human body reconstruction have achieved notable success in creating animatable avatars. However, there are ongoing challenges to fully exploit the SMPL model's prior knowledge and enhance the visual…

图形学 · 计算机科学 2025-02-28 Mengtian Li , Shengxiang Yao , Chen Kai , Zhifeng Xie , Keyu Chen , Yu-Gang Jiang

We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Shenhan Qian , Tobias Kirschstein , Liam Schoneveld , Davide Davoli , Simon Giebenhain , Matthias Nießner

We propose SplatArmor, a novel approach for recovering detailed and animatable human models by `armoring' a parameterized body model with 3D Gaussians. Our approach represents the human as a set of 3D Gaussians within a canonical space,…

计算机视觉与模式识别 · 计算机科学 2023-11-21 Rohit Jena , Ganesh Subramanian Iyer , Siddharth Choudhary , Brandon Smith , Pratik Chaudhari , James Gee

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

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

Modeling animatable human avatars from videos is a long-standing and challenging problem. While conventional methods require per-instance optimization, recent feed-forward methods have been proposed to generate 3D Gaussians with a learnable…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Yifan Liu , Shengjun Zhang , Chensheng Dai , Yang Chen , Hao Liu , Chen Li , Yueqi Duan

We introduce HyperGaussians, a novel extension of 3D Gaussian Splatting for high-quality animatable face avatars. Creating such detailed face avatars from videos is a challenging problem and has numerous applications in augmented and…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Gent Serifi , Marcel C. Buehler

We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Devdoot Chatterjee , Zakaria Laskar , C. V. Jawahar

The emergence of neural rendering has significantly advanced the rendering quality of 3D human avatars, with the recently popular 3DGS technique enabling real-time performance. However, SMPL-driven 3DGS human avatars still struggle to…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Wangze Xu , Yifan Zhan , Zhihang Zhong , Xiao Sun

Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a…

图形学 · 计算机科学 2024-02-08 Lin Gao , Jie Yang , Bo-Tao Zhang , Jia-Mu Sun , Yu-Jie Yuan , Hongbo Fu , Yu-Kun Lai

We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Zhiyin Qian , Shaofei Wang , Marko Mihajlovic , Andreas Geiger , Siyu Tang

Photorealistic and controllable human avatars have gained popularity in the research community thanks to rapid advances in neural rendering, providing fast and realistic synthesis tools. However, a limitation of current solutions is the…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Mohamed Ilyes Lakhal , Richard Bowden

High-quality, animatable 3D human avatar reconstruction from monocular videos offers significant potential for reducing reliance on complex hardware, making it highly practical for applications in game development, augmented reality, and…

计算机视觉与模式识别 · 计算机科学 2025-05-02 Xia Yuan , Hai Yuan , Wenyi Ge , Ying Fu , Xi Wu , Guanyu Xing

Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve high-quality novel…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Yujiao Jiang , Qingmin Liao , Xiaoyu Li , Li Ma , Qi Zhang , Chaopeng Zhang , Zongqing Lu , Ying Shan

We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion…

图形学 · 计算机科学 2024-03-11 Zhijing Shao , Zhaolong Wang , Zhuang Li , Duotun Wang , Xiangru Lin , Yu Zhang , Mingming Fan , Zeyu Wang

Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators rely on mesh-based rasterization with limited visual realism, and their support for…