中文
相关论文

相关论文: Faster Image2Video Generation: A Closer Look at CL…

200 篇论文

Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long inference latency, which largely…

计算机视觉与模式识别 · 计算机科学 2022-07-12 Long Zhuo , Guangcong Wang , Shikai Li , Wayne Wu , Ziwei Liu

The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they…

硬件体系结构 · 计算机科学 2025-11-18 Wenxuan Miao , Yulin Sun , Aiyue Chen , Jing Lin , Yiwu Yao , Yiming Gan , Jieru Zhao , Jingwen Leng , Mingyi Guo , Yu Feng

Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Sihyun Yu , Weili Nie , De-An Huang , Boyi Li , Jinwoo Shin , Anima Anandkumar

Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Guantao Chen , Shikang Zheng , Yuqi Lin , Linfeng Zhang

Video-to-video translation aims to generate video frames of a target domain from an input video. Despite its usefulness, the existing networks require enormous computations, necessitating their model compression for wide use. While there…

计算机视觉与模式识别 · 计算机科学 2023-10-05 Chaeyeon Chung , Yeojeong Park , Seunghwan Choi , Munkhsoyol Ganbat , Jaegul Choo

Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Hongyu An , Xinfeng Zhang , Shijie Zhao , Li Zhang , Ruiqin Xiong

Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs. This…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Haocheng Xi , Shuo Yang , Yilong Zhao , Chenfeng Xu , Muyang Li , Xiuyu Li , Yujun Lin , Han Cai , Jintao Zhang , Dacheng Li , Jianfei Chen , Ion Stoica , Kurt Keutzer , Song Han

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Shai Yehezkel , Shahar Yadin , Noam Elata , Yaron Ostrovsky-Berman , Bahjat Kawar

Text-driven video generation witnesses rapid progress. However, merely using text prompts is not enough to depict the desired subject appearance that accurately aligns with users' intents, especially for customized content creation. In this…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Yuming Jiang , Tianxing Wu , Shuai Yang , Chenyang Si , Dahua Lin , Yu Qiao , Chen Change Loy , Ziwei Liu

Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation process is an important goal moving forward and recent…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Zhengfei Kuang , Shengqu Cai , Hao He , Yinghao Xu , Hongsheng Li , Leonidas Guibas , Gordon Wetzstein

Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on latent computation becomes inadequate. A promising approach…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Liangbin Xie , Yu Li , Shian Du , Menghan Xia , Xintao Wang , Fanghua Yu , Ziyan Chen , Pengfei Wan , Jiantao Zhou , Chao Dong

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Junyang Chen , Jiangxin Dong , Long Sun , Yixin Yang , Jinshan Pan

Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-video (T2V) applications. However, the computational demands…

计算机视觉与模式识别 · 计算机科学 2025-01-29 Wenfeng Lin , Jiangchuan Wei , Boyuan Liu , Yichen Zhang , Shiyue Yan , Mingyu Guo

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…

计算机视觉与模式识别 · 计算机科学 2022-09-28 Yulin Wang , Yang Yue , Xinhong Xu , Ali Hassani , Victor Kulikov , Nikita Orlov , Shiji Song , Humphrey Shi , Gao Huang

This paper explores the innovative application of Stable Video Diffusion (SVD), a diffusion model that revolutionizes the creation of dynamic video content from static images. As digital media and design industries accelerate, SVD emerges…

人机交互 · 计算机科学 2024-05-24 Elijah Miller , Thomas Dupont , Mingming Wang

Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT)…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yue Ma , Zhikai Wang , Tianhao Ren , Mingzhe Zheng , Hongyu Liu , Jiayi Guo , Kunyu Feng , Yuxuan Xue , Zixiang Zhao , Konrad Schindler , Qifeng Chen , Linfeng Zhang

In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Zhe Li , Hadrien Reynaud , Mischa Dombrowski , Sarah Cechnicka , Franciskus Xaverius Erick , Bernhard Kainz

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Antoine Miech , Jean-Baptiste Alayrac , Ivan Laptev , Josef Sivic , Andrew Zisserman

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Kumara Kahatapitiya , Adil Karjauv , Davide Abati , Fatih Porikli , Yuki M. Asano , Amirhossein Habibian

Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Yushi Huang , Xingtong Ge , Ruihao Gong , Chengtao Lv , Jun Zhang
‹ 上一页 1 2 3 10 下一页 ›