English
Related papers

Related papers: Motion-Aware Caching for Efficient Autoregressive …

200 papers

Extracting human motion from large-scale web videos offers a scalable solution to the data scarcity issue in character animation. However, some human parts in many video frames cannot be seen due to off-screen captures or occlusions. It…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Boyuan Li , Sipeng Zheng , Bin Cao , Ruihua Song , Zongqing Lu

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Tao Wu , Yong Zhang , Xintao Wang , Xianpan Zhou , Guangcong Zheng , Zhongang Qi , Ying Shan , Xi Li

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature caching offers a promising training-free acceleration solution by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Fanpu Cao , Yaofo Chen , Zeng You , Wei Luo

Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for efficient deployment. While existing sparse attention solutions…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Chengtao Lv , Yumeng Shi , Yushi Huang , Ruihao Gong , Shen Ren , Wenya Wang

Generating videos with realistic and physically plausible motion is one of the main recent challenges in computer vision. While diffusion models are achieving compelling results in image generation, video diffusion models are limited by…

Machine Learning · Computer Science 2024-10-28 Luca Savant Aira , Antonio Montanaro , Emanuele Aiello , Diego Valsesia , Enrico Magli

Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents but varying in…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Jingyuan Zhu , Huimin Ma , Jiansheng Chen , Jian Yuan

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yang Yang , Tianyi Zhang , Wei Huang , Jinwei Chen , Boxi Wu , Xiaofei He , Deng Cai , Bo Li , Peng-Tao Jiang

Controllable generation of 3D human motions becomes an important topic as the world embraces digital transformation. Existing works, though making promising progress with the advent of diffusion models, heavily rely on meticulously captured…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Nhat M. Hoang , Kehong Gong , Chuan Guo , Michael Bi Mi

Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Tianrui Zhu , Shiyi Zhang , Zhirui Sun , Jingqi Tian , Yansong Tang

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: "When to cache" and "How to use…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Jiazi Bu , Pengyang Ling , Yujie Zhou , Yibin Wang , Yuhang Zang , Dahua Lin , Jiaqi Wang

We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Ruihang Chu , Yefei He , Zhekai Chen , Shiwei Zhang , Xiaogang Xu , Bin Xia , Dingdong Wang , Hongwei Yi , Xihui Liu , Hengshuang Zhao , Yu Liu , Yingya Zhang , Yujiu Yang

Video generation remains a challenging task due to spatiotemporal complexity and the requirement of synthesizing diverse motions with temporal consistency. Previous works attempt to generate videos in arbitrary lengths either in an…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Xiaoqian Shen , Xiang Li , Mohamed Elhoseiny

We present ActionPlan, a unified motion diffusion framework that bridges real-time streaming with high-quality offline generation within a single model. The core idea is to introduce a per-frame action plan: the model predicts frame-level…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Eric Nazarenus , Chuqiao Li , Yannan He , Xianghui Xie , Jan Eric Lenssen , Gerard Pons-Moll

Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a…

Interactive motion synthesis is essential in creating immersive experiences in entertainment applications, such as video games and virtual reality. However, generating animations that are both high-quality and contextually responsive…

Computer Vision and Pattern Recognition · Computer Science 2024-01-15 Tianyu Li , Calvin Qiao , Guanqiao Ren , KangKang Yin , Sehoon Ha

Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting to understand diverse motion categories specified in prompts.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Zixuan Wang , Ziqin Zhou , Feng Chen , Duo Peng , Yixin Hu , Changsheng Li , Yinjie Lei

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Kumara Kahatapitiya , Michael S. Ryoo

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from…

Multimedia · Computer Science 2025-01-09 Desen Sun , Henry Tian , Tim Lu , Sihang Liu

Advancements in attention mechanisms have led to significant performance improvements in a variety of areas in machine learning due to its ability to enable the dynamic modeling of temporal sequences. A particular area in computer vision…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Brennan Gebotys , Alexander Wong , David A. Clausi

We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jingyuan Qi , Zhiyang Xu , Qifan Wang , Lifu Huang