DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

Ziqiao Peng; Yanbo Fan; Haoyu Wu; Xuan Wang; Hongyan Liu; Jun He; Zhaoxin Fan

doi:10.1109/cvpr52734.2025.01961

CVPR2025顶会

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

Ziqiao Peng, Yanbo Fan, Haoyu Wu, Xuan Wang, Hongyan Liu, Jun He, Zhaoxin Fan

DOI 出版方

2025年份

8顶会引用

摘要

ralness and expressiveness of 3D talking heads in dualspeaker conversations. We recommend watching the supplementary video: https://ziqiaopeng.github. io/dualtalk

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。

核心论断
谁在沿用
横向对比
局限

你的问题

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始，无需绑卡

引用它的顶会 Paper8

OmniSync: Towards Universal Lip Synchronization via Diffusion TransformersZiqiao Peng, Jiwen Liu, Haoxian Zhang, Xiaoqiang Liu 等NeurIPS 2025 · 被引用 30 次
UniLS: End-to-End Audio-Driven Avatars for Unified Listening and SpeakingXuangeng Chu, Ruicong Liu, Yifei Huang, Yun Liu 等CVPR 2026 · 被引用 12 次
ActAvatar: Temporally-Aware Precise Action Control for Talking AvatarsZiqiao Peng, Yi Chen, Yifeng Ma, Guozhen Zhang 等CVPR 2026 · 被引用 7 次
DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking HeadsXiaoxi Liang, Yanbo Fan, Qiya Yang, Xuan Wang 等ICCV 2025 · 被引用 2 次
RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn ConversationPeng Chen, Xiaobao Wei, Yi Yang, Naiming Yao 等IEEE VR 2026

问问它们各自怎么用它

它引用的顶会 Paper18

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 被引用 9,451 次
MeshTalk: 3D Face Animation from Speech using Cross-Modality DisentanglementAlexander Richard, Michael Zollhöfer, Yandong Wen, Fernando De la Torre 等ICCV 2021 · 被引用 272 次
FaceFormer: Speech-Driven 3D Facial Animation with TransformersYingruo Fan, Zhaojiang Lin, Jun Saito, Wenping Wang 等CVPR 2022 · 被引用 218 次
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face AnimationZiqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu 等ICCV 2023 · 被引用 192 次
Imitator: Personalized Speech-driven 3D Facial AnimationBalamurugan Thambiraja, Ikhsanul Habibie, Sadegh Aliakbarian, Darren Cosker 等ICCV 2023 · 被引用 98 次

摘要

问问这篇 Paper

智能体会读完全文。

引用它的顶会 Paper8

它引用的顶会 Paper18

相关 Paper