中文
相关论文

相关论文: Hallo-Live: Real-Time Streaming Joint Audio-Video …

200 篇论文

Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon drift of current diffusion models. We present Live Avatar, an…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Yubo Huang , Hailong Guo , Fangtai Wu , Weiqiang Wang , Shifeng Zhang , Shijie Huang , Qijun Gan , Lin Liu , Sirui Zhao , Enhong Chen , Jiaming Liu , Steven Hoi

Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Haojie Yu , Zhaonian Wang , Yihan Pan , Meng Cheng , Hao Yang , Chao Wang , Tao Xie , Xiaoming Xu , Xiaoming Wei , Xunliang Cai

Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural facial expressions, and high-fidelity body motion dynamics. We…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Jiahao Cui , Yan Chen , Mingwang Xu , Hanlin Shang , Yuxuan Chen , Yun Zhan , Zilong Dong , Yao Yao , Jingdong Wang , Siyu Zhu

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Beijia Lu , Ziyi Chen , Jing Xiao , Jun-Yan Zhu

The field of portrait image animation, driven by speech audio input, has experienced significant advancements in the generation of realistic and dynamic portraits. This research delves into the complexities of synchronizing facial movements…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Mingwang Xu , Hui Li , Qingkun Su , Hanlin Shang , Liwei Zhang , Ce Liu , Jingdong Wang , Yao Yao , Siyu Zhu

Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems. However, the simultaneous denoising of all video frames with bidirectional attention via an iterative process in diffusion…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Ethan Chern , Zhulin Hu , Bohao Tang , Jiadi Su , Steffi Chern , Zhijie Deng , Pengfei Liu

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Xiangyu Liu , Feng Gao , Xiaomei Zhang , Yong Zhang , Xiaoming Wei , Zhen Lei , Xiangyu Zhu

Current diffusion-based portrait animation models predominantly focus on enhancing visual quality and expression realism, while overlooking generation latency and real-time performance, which restricts their application range in the live…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Zhiyuan Li , Chi-Man Pun , Chen Fang , Jue Wang , Xiaodong Cun

Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA inevitably loses distant history during long video…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Ruibin Li , Tao Yang , Fangzhou Ai , Tianhe Wu , Shilei Wen , Bingyue Peng , Lei Zhang

Video generation is rapidly evolving towards unified audio-video generation. In this paper, we present ALIVE, a generation model that adapts a pretrained Text-to-Video (T2V) model to Sora-style audio-video generation and animation. In…

计算机视觉与模式识别 · 计算机科学 2026-02-11 Ying Guo , Qijun Gan , Yifu Zhang , Jinlai Liu , Yifei Hu , Pan Xie , Dongjun Qian , Yu Zhang , Ruiqi Li , Yuqi Zhang , Ruibiao Lu , Xiaofeng Mei , Bo Han , Xiang Yin , Bingyue Peng , Zehuan Yuan

Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remarkable success, their non-causal architecture and high…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Zhiyao Sun , Ziqiao Peng , Yifeng Ma , Yi Chen , Zhengguang Zhou , Zixiang Zhou , Guozhen Zhang , Youliang Zhang , Yuan Zhou , Qinglin Lu , Yong-Jin Liu

Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models often suffer from prohibitive computational costs, while…

计算机视觉与模式识别 · 计算机科学 2026-02-12 Tan Yu , Qian Qiao , Le Shen , Ke Zhou , Jincheng Hu , Dian Sheng , Bo Hu , Haoming Qin , Jun Gao , Changhai Zhou , Shunshun Yin , Siyuan Liu

Diffusion models have significantly advanced the field of talking head generation (THG). However, slow inference speeds and prevalent non-autoregressive paradigms severely constrain the application of diffusion-based THG models. In this…

计算机视觉与模式识别 · 计算机科学 2026-01-30 Haotian Wang , Yuzhe Weng , Jun Du , Haoran Xu , Xiaoyan Wu , Shan He , Bing Yin , Cong Liu , Qingfeng Liu

Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Jiahao Cui , Hui Li , Yao Yao , Hao Zhu , Hanlin Shang , Kaihui Cheng , Hang Zhou , Siyu Zhu , Jingdong Wang

Deploying massive diffusion models for real-time, infinite-duration, audio-driven avatar generation presents a significant engineering challenge, primarily due to the conflict between computational load and strict latency constraints.…

计算机视觉与模式识别 · 计算机科学 2026-01-07 Le Shen , Qian Qiao , Tan Yu , Ke Zhou , Tianhang Yu , Yu Zhan , Zhenjie Wang , Ming Tao , Shunshun Yin , Siyuan Liu

Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities. Unlike typical (non-streaming) voice conversion, which can leverage the entire…

音频与语音处理 · 电气工程与系统科学 2023-06-01 Ziqian Ning , Yuepeng Jiang , Pengcheng Zhu , Jixun Yao , Shuai Wang , Lei Xie , Mengxiao Bi

Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run within a strict playback budget. These requirements are…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Linrui Tian , Qi Wang , Bang Zhang

Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limits practical applications. Despite the development of various…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Tianyun Zhong , Chao Liang , Jianwen Jiang , Gaojie Lin , Jiaqi Yang , Zhou Zhao

Diffusion-based video super-resolution (VSR) has recently achieved remarkable fidelity but still suffers from prohibitive sampling costs. While distribution matching distillation (DMD) can accelerate diffusion models toward one-step…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Zhengyao Lv , Menghan Xia , Xintao Wang , Kwan-Yee K. Wong
‹ 上一页 1 2 3 10 下一页 ›