English
Related papers

Related papers: MonarchRT: Efficient Attention for Real-Time Video…

200 papers

Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Hyeonho Jeong , Geon Yeong Park , Jong Chul Ye

Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver promising results, largely due to the challenges of scaling…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yuhan Wang , Fangzhou Hong , Shuai Yang , Liming Jiang , Wayne Wu , Chen Change Loy

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Machine Learning · Computer Science 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xuanyi Zhou , Qiuyang Mang , Shuo Yang , Haocheng Xi , Jintao Zhang , Huanzhi Mao , Joseph E. Gonzalez , Kurt Keutzer , Ion Stoica , Alvin Cheung

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Yongji Long , Shijun Liang , Jintao Li , Yun Li

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Gedas Bertasius , Heng Wang , Lorenzo Torresani

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

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xianbing Sun , Zhikai Zhu , Zhengyu Lou , Bo Yang , Jinyang Tang , Liqing Zhang , He Wang , Jianfu Zhang

Despite the remarkable generation quality of video Diffusion Transformer (DiT) models, their practical deployment is severely hindered by extensive computational requirements. This inefficiency stems from two key challenges: the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yuechen Zhang , Jinbo Xing , Bin Xia , Shaoteng Liu , Bohao Peng , Xin Tao , Pengfei Wan , Eric Lo , Jiaya Jia

Text-to-video diffusion models have made remarkable advancements. Driven by their ability to generate temporally coherent videos, research on zero-shot video editing using these fundamental models has expanded rapidly. To enhance editing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Lingling Cai , Kang Zhao , Hangjie Yuan , Yingya Zhang , Shiwei Zhang , Kejie Huang

Designing sparse attention for diffusion transformers requires reconciling two-dimensional spatial locality with GPU efficiency, a trade-off that current methods struggle to achieve. Existing approaches enforce two-dimensional spatial…

Artificial Intelligence · Computer Science 2025-10-01 Shaoyi Zheng , Wenbo Lu , Yuxuan Xia , Haomin Liu , Shengjie Wang

For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents a significant challenge. In this paper, we propose a new…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Yupeng Zhou , Daquan Zhou , Ming-Ming Cheng , Jiashi Feng , Qibin Hou

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chao Yuan , Pan Li

Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Xin Zhou , Dingkang Liang , Kaijin Chen , Tianrui Feng , Xiwu Chen , Hongkai Lin , Yikang Ding , Feiyang Tan , Hengshuang Zhao , Xiang Bai

While diffusion language models (DLMs) offer a promising alternative to autoregressive models (ARs), existing open-source DLMs suffer from high inference latency. This bottleneck is mainly due to the attention's quadratic complexity with…

Computation and Language · Computer Science 2025-09-30 Zeqing Wang , Gongfan Fang , Xinyin Ma , Xingyi Yang , Xinchao Wang

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xuan Shen , Weize Ma , Yufa Zhou , Enhao Tang , Yanyue Xie , Zhengang Li , Yifan Gong , Quanyi Wang , Henghui Ding , Yiwei Wang , Yanzhi Wang , Pu Zhao , Jun Lin , Jiuxiang Gu

Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Mahdi Saleh , Yige Wang , Nassir Navab , Benjamin Busam , Federico Tombari

The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hang Guo , Zhaoyang Jia , Jiahao Li , Bin Li , Yuanhao Cai , Jiangshan Wang , Yawei Li , Yan Lu

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Jing Wang , Ao Ma , Jiasong Feng , Dawei Leng , Yuhui Yin , Xiaodan Liang