English
Related papers

Related papers: Accelerating Video Generation Inference with Seque…

200 papers

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-02 Xin Tan , Yuetao Chen , Yimin Jiang , Xing Chen , Kun Yan , Nan Duan , Yibo Zhu , Daxin Jiang , Hong Xu

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Kai Wang , Hao Luo , Yibing Song , Gao Huang , Fan Wang , Yang You

We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies, with attention to computational and dataset efficiency. To capture long spatio-temporal dependencies, our approach…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Partha Ghosh , Soubhik Sanyal , Cordelia Schmid , Bernhard Schölkopf

Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a few seconds of video. This inefficiency poses a critical…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Jieying Chen , Jeffrey Hu , Joan Lasenby , Ayush Tewari

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Dong Liu , Yanxuan Yu , Ben Lengerich , Ying Nian Wu

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Xunnong Xu , Mengying Cao

To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by causal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hongzhou Zhu , Min Zhao , Guande He , Hang Su , Chongxuan Li , Jun Zhu

We propose a novel block for \emph{causal} video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each dimension: gated linear recurrent units (LRUs) perform information mixing over time, self-attention…

We introduce a class of causal video understanding models that aims to improve efficiency of video processing by maximising throughput, minimising latency, and reducing the number of clock cycles. Leveraging operation pipelining and…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Joao Carreira , Viorica Patraucean , Laurent Mazare , Andrew Zisserman , Simon Osindero

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Yongqi Yang , Huayang Huang , Xu Peng , Xiaobin Hu , Donghao Luo , Jiangning Zhang , Chengjie Wang , Yu Wu

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Shufan Li , Konstantinos Kallidromitis , Akash Gokul , Arsh Koneru , Yusuke Kato , Kazuki Kozuka , Aditya Grover

Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Ruichen Chen , Keith G. Mills , Liyao Jiang , Chao Gao , Di Niu

Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Aiyue Chen , Bin Dong , Jingru Li , Jing Lin , Kun Tian , Yiwu Yao , Gongyi Wang

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Tianxiong Zhong , Xingye Tian , Boyuan Jiang , Xuebo Wang , Xin Tao , Pengfei Wan , Zhiwei Zhang

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Xuzhe Zheng , Yuexiao Ma , Jing Xu , Xiawu Zheng , Rongrong Ji , Fei Chao

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Fanshuai Meng , Weijia Jia , Wei Zhao

Leveraging pre-trained Diffusion Transformers (DiTs) for high-resolution (HR) image synthesis often leads to spatial layout collapse and degraded texture fidelity. Prior work mitigates these issues with complex pipelines that first perform…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Yiyang Ma , Feng Zhou , Xuedan Yin , Pu Cao , Yonghao Dang , Jianqin Yin

The rapid progress in artificial intelligence-generated content (AIGC), especially with diffusion models, has significantly advanced development of high-quality video generation. However, current video diffusion models exhibit demanding…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Zheng Zhan , Yushu Wu , Yifan Gong , Zichong Meng , Zhenglun Kong , Changdi Yang , Geng Yuan , Pu Zhao , Wei Niu , Yanzhi Wang

Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Fangqiu Yi , Jingyu Xu , Jiawei Shao , Chi Zhang , Xuelong Li

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Sheng Li , Yang Sui , Junhao Ran , Bo Yuan , Yue Dai , Xulong Tang