English
Related papers

Related papers: TurboTalk: Progressive Distillation for One-Step A…

200 papers

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xiangyu Fan , Zesong Qiu , Zhuguanyu Wu , Fanzhou Wang , Zhiqian Lin , Tianxiang Ren , Dahua Lin , Ruihao Gong , Lei Yang

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-19 Liang Xu , Longfei Felix Yan , W. Bastiaan Kleijn

Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Xusen Sun , Longhao Zhang , Hao Zhu , Peng Zhang , Bang Zhang , Xinya Ji , Kangneng Zhou , Daiheng Gao , Liefeng Bo , Xun Cao

Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yuanzhi Zhu , Hanshu Yan , Huan Yang , Kai Zhang , Junnan Li

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…

Computer Vision and Pattern Recognition · Computer Science 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

Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated global body movements, and the dynamic background. To address…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Mengchao Wang , Qiang Wang , Fan Jiang , Yaqi Fan , Yunpeng Zhang , Yonggang Qi , Kun Zhao , Mu Xu

Diffusion models have achieved remarkable progress in the field of video generation. However, their iterative denoising nature requires a large number of inference steps to generate a video, which is slow and computationally expensive. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Haiyu Zhang , Xinyuan Chen , Yaohui Wang , Xihui Liu , Yunhong Wang , Yu Qiao

Diffusion models excel at producing high-quality samples but naively require hundreds of iterations, prompting multiple attempts to distill the generation process into a faster network. However, many existing approaches suffer from a…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Zhengyang Geng , Ashwini Pokle , J. Zico Kolter

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Jintao Zhang , Kaiwen Zheng , Kai Jiang , Haoxu Wang , Ion Stoica , Joseph E. Gonzalez , Jianfei Chen , Jun Zhu

We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data given noisy data along the sampling trajectory.…

Machine Learning · Computer Science 2024-06-07 Tim Salimans , Thomas Mensink , Jonathan Heek , Emiel Hoogeboom

The generation of emotional talking faces from a single portrait image remains a significant challenge. The simultaneous achievement of expressive emotional talking and accurate lip-sync is particularly difficult, as expressiveness is often…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Chenxu Zhang , Chao Wang , Jianfeng Zhang , Hongyi Xu , Guoxian Song , You Xie , Linjie Luo , Yapeng Tian , Xiaohu Guo , Jiashi Feng

Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio-visual diffusion models remain too slow for interactive use…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Chunyu Li , Jiaye Li , Ruiqiao Mei , Haoyuan Xia , Hao Zhu , Jingdong Wang , Siyu Zhu

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-14 Rongjie Huang , Zhou Zhao , Huadai Liu , Jinglin Liu , Chenye Cui , Yi Ren

Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities throughout denoising via pervasive attention, treating…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Zhen Ye , Xu Tan , Aoxiong Yin , Hongzhan Lin , Guangyan Zhang , Peiwen Sun , Yiming Li , Chi-Min Chan , Wei Ye , Shikun Zhang , Wei Xue

Diffusion-based voice conversion (VC) techniques such as VoiceGrad have attracted interest because of their high VC performance in terms of speech quality and speaker similarity. However, a notable limitation is the slow inference caused by…

Sound · Computer Science 2024-09-05 Takuhiro Kaneko , Hirokazu Kameoka , Kou Tanaka , Yuto Kondo

Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be degraded. Recent studies show that incorporating a GAN…

Machine Learning · Computer Science 2025-06-12 Bowen Zheng , Tianming Yang

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Jinxiu Liu , Xuanming Liu , Kangfu Mei , Yandong Wen , Ming-Hsuan Yang , Weiyang Liu

Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yuyang You , Yongzhi Li , Jiahui Li , Yadong Mu , Quan Chen , Peng Jiang

Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Yanxiao Sun , Jiafu Wu , Yun Cao , Chengming Xu , Yabiao Wang , Weijian Cao , Donghao Luo , Chengjie Wang , Yanwei Fu