English
Related papers

Related papers: {\Phi}-Noise: Training-Free Temporal Video Conditi…

200 papers

In recent years, diffusion models have made remarkable strides in text-to-video generation, sparking a quest for enhanced control over video outputs to more accurately reflect user intentions. Traditional efforts predominantly focus on…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Mingxiao Li , Bo Wan , Marie-Francine Moens , Tinne Tuytelaars

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Aniruddha Mahapatra , Long Mai , David Bourgin , Yitian Zhang , Feng Liu

Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Haojie Yu , Zhaonian Wang , Yihan Pan , Meng Cheng , Hao Yang , Chao Wang , Tao Xie , Xiaoming Xu , Xiaoming Wei , Xunliang Cai

Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely on conditioning: frame-level signals are domain-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Saurabh Pathak , Elahe Arani , Mykola Pechenizkiy , Bahram Zonooz

Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Chao Liu , Arash Vahdat

In many video processing tasks, leveraging large-scale image datasets is a common strategy, as image data is more abundant and facilitates comprehensive knowledge transfer. A typical approach for simulating video from static images involves…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Suhwan Cho , Minhyeok Lee , Jungho Lee , Sangyoun Lee

Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Chenyu Wang , Shuo Yan , Yixuan Chen , Yujiang Wang , Mingzhi Dong , Xiaochen Yang , Dongsheng Li , Robert P. Dick , Qin Lv , Fan Yang , Tun Lu , Ning Gu , Li Shang

Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Desai Xie , Zhan Xu , Yicong Hong , Hao Tan , Difan Liu , Feng Liu , Arie Kaufman , Yang Zhou

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

Machine Learning · Computer Science 2025-04-04 Dohyun Kim , Sehwan Park , Geonhee Han , Seung Wook Kim , Paul Hongsuck Seo

Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Mehdi Noroozi , Alberto Gil Ramos , Luca Morreale , Ruchika Chavhan , Malcolm Chadwick , Abhinav Mehrotra , Sourav Bhattacharya

In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Zhengyao Lv , Chenyang Si , Junhao Song , Zhenyu Yang , Yu Qiao , Ziwei Liu , Kwan-Yee K. Wong

We introduce nested diffusion models, an efficient and powerful hierarchical generative framework that substantially enhances the generation quality of diffusion models, particularly for images of complex scenes. Our approach employs a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Xiao Zhang , Ruoxi Jiang , Rebecca Willett , Michael Maire

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Jiaqi Liu , Tao Huang , Chang Xu

Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Yibo Zhao , Hengjia Li , Xiaofei He , Boxi Wu

We present MoCA-Video, a training-free framework for semantic mixing in videos. Operating in the latent space of a frozen video diffusion model, MoCA-Video utilizes class-agnostic segmentation with diagonal denoising scheduler to localize…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Tong Zhang , Juan C Leon Alcazar , Victor Escorcia , Bernard Ghanem

Gestures are essential for enhancing co-speech communication, offering visual emphasis and complementing verbal interactions. While prior work has concentrated on point-level motion or fully supervised data-driven methods, we focus on…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Jiahui Chen , Yang Huan , Runhua Shi , Chanfan Ding , Xiaoqi Mo , Siyu Xiong , Yinong He

Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Yu Zeng , Charles Ochoa , Mingyuan Zhou , Vishal M. Patel , Vitor Guizilini , Rowan McAllister

In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a…

Machine Learning · Computer Science 2023-02-07 Joost van Amersfoort , Anitha Kannan , Marc'Aurelio Ranzato , Arthur Szlam , Du Tran , Soumith Chintala

Recent large-scale pre-trained diffusion models have demonstrated a powerful generative ability to produce high-quality videos from detailed text descriptions. However, exerting control over the motion of objects in videos generated by any…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Changgu Chen , Junwei Shu , Gaoqi He , Changbo Wang , Yang Li

Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Sherwin Bahmani , Ivan Skorokhodov , Guocheng Qian , Aliaksandr Siarohin , Willi Menapace , Andrea Tagliasacchi , David B. Lindell , Sergey Tulyakov