中文
相关论文

相关论文: D^3-Talker: Dual-Branch Decoupled Deformation Fiel…

200 篇论文

We propose GaussianTalker, a novel framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Kyusun Cho , Joungbin Lee , Heeji Yoon , Yeobin Hong , Jaehoon Ko , Sangjun Ahn , Seungryong Kim

Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head…

计算机视觉与模式识别 · 计算机科学 2025-07-11 Wentao Hu , Shunkai Li , Ziqiao Peng , Haoxian Zhang , Fan Shi , Xiaoqiang Liu , Pengfei Wan , Di Zhang , Hui Tian

Recent works on audio-driven talking head synthesis using Neural Radiance Fields (NeRF) have achieved impressive results. However, due to inadequate pose and expression control caused by NeRF implicit representation, these methods still…

计算机视觉与模式识别 · 计算机科学 2024-08-12 Hongyun Yu , Zhan Qu , Qihang Yu , Jianchuan Chen , Zhonghua Jiang , Zhiwen Chen , Shengyu Zhang , Jimin Xu , Fei Wu , Chengfei Lv , Gang Yu

Talking head synthesis with arbitrary speech audio is a crucial challenge in the field of digital humans. Recently, methods based on radiance fields have received increasing attention due to their ability to synthesize high-fidelity and…

声音 · 计算机科学 2024-12-12 Yifan Xie , Tao Feng , Xin Zhang , Xiangyang Luo , Zixuan Guo , Weijiang Yu , Heng Chang , Fei Ma , Fei Richard Yu

Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions by directly…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Jiahe Li , Jiawei Zhang , Xiao Bai , Jin Zheng , Xin Ning , Jun Zhou , Lin Gu

High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based methods typically rely on identity-specific models, limiting cross-identity generalization. To…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Peng Jia , Zhen Xiao , Jia Li , Xueliang Liu , Zhenzhen Hu , Lingyun Yu

This paper presents EGSTalker, a real-time audio-driven talking head generation framework based on 3D Gaussian Splatting (3DGS). Designed to enhance both speed and visual fidelity, EGSTalker requires only 3-5 minutes of training video to…

声音 · 计算机科学 2025-10-13 Tianheng Zhu , Yinfeng Yu , Liejun Wang , Fuchun Sun , Wendong Zheng

Speech-driven 3D talking head generation aims to produce lifelike facial animations precisely synchronized with speech. While considerable progress has been made in achieving high lip-synchronization accuracy, existing methods largely…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Bin Wang , Yang Xu , Huan Zhao , Hao Zhang , Zixing Zhang

Audio-driven talking head generation is a core component of digital avatars, and 3D Gaussian Splatting has shown strong performance in real-time rendering of high-fidelity talking heads. However, achieving precise control over fine-grained…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Shaoyang Xie , Xiaofeng Cong , Baosheng Yu , Zhipeng Gui , Jie Gui , Yuan Yan Tang , James Tin-Yau Kwok

3D Gaussian splatting-based talking head synthesis has recently gained attention for its ability to render high-fidelity images with real-time inference speed. However, since it is typically trained on only a short video that lacks the…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Junuk Cha , Seongro Yoon , Valeriya Strizhkova , Francois Bremond , Seungryul Baek

Speech-driven three-dimensional (3D) facial animation synthesis aims to build a mapping from one-dimensional (1D) speech signals to time-varying 3D facial motion signals. Current methods still face challenges in maintaining lip-sync…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Bin Liu , Zhixiang Xiong , Zhifen He , Bo Li

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Kaijun Deng , Dezhi Zheng , Jindong Xie , Jinbao Wang , Weicheng Xie , Linlin Shen , Siyang Song

Talking head synthesis is to synthesize a lip-synchronized talking head video using audio. Recently, the capability of NeRF to enhance the realism and texture details of synthesized talking heads has attracted the attention of researchers.…

图形学 · 计算机科学 2025-02-21 Xiaoxing Liu , Zhilei Liu , Chongke Bi

Audio-driven talking head generation is crucial for applications in virtual reality, digital avatars, and film production. While NeRF-based methods enable high-fidelity reconstruction, they suffer from low rendering efficiency and…

声音 · 计算机科学 2025-09-23 Tianheng Zhu , Yinfeng Yu , Liejun Wang , Fuchun Sun , Wendong Zheng

We present GStalker, a 3D audio-driven talking face generation model with Gaussian Splatting for both fast training (40 minutes) and real-time rendering (125 FPS) with a 3$\sim$5 minute video for training material, in comparison with…

计算机视觉与模式识别 · 计算机科学 2024-05-01 Bo Chen , Shoukang Hu , Qi Chen , Chenpeng Du , Ran Yi , Yanmin Qian , Xie Chen

We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress in the field, prior methods still suffer from multi-view…

计算机视觉与模式识别 · 计算机科学 2024-08-02 Qianyun He , Xinya Ji , Yicheng Gong , Yuanxun Lu , Zhengyu Diao , Linjia Huang , Yao Yao , Siyu Zhu , Zhan Ma , Songcen Xu , Xiaofei Wu , Zixiao Zhang , Xun Cao , Hao Zhu

Real-time talking head synthesis increasingly relies on deformable 3D Gaussian Splatting (3DGS) due to its low latency. Tri-planes are the standard choice for encoding Gaussians prior to deformation, since they provide a continuous domain…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Arpita Saggar , Jonathan C. Darling , Duygu Sarikaya , David C. Hogg

Recent methods for audio-driven talking head synthesis often optimize neural radiance fields (NeRF) on a monocular talking portrait video, leveraging its capability to render high-fidelity and 3D-consistent novel-view frames. However, they…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Jaehoon Ko , Kyusun Cho , Joungbin Lee , Heeji Yoon , Sangmin Lee , Sangjun Ahn , Seungryong Kim

We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio. To capture the expressive, detailed nature of human heads, including…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Shivangi Aneja , Artem Sevastopolsky , Tobias Kirschstein , Justus Thies , Angela Dai , Matthias Nießner

Audio-driven 3D talking avatar generation is increasingly important in virtual communication, digital humans, and interactive media, where avatars must preserve identity, synchronize lip motion with speech, express emotion, and exhibit…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Zhongju Wang , Zhenhong Sun , Beier Wang , Yifu Wang , Daoyi Dong , Huadong Mo , Hongdong Li
‹ 上一页 1 2 3 10 下一页 ›