Efficient Video Diffusion Models: Advancements and Challenges

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Shitong, Bai, Lichen, Wan, Pengfei, Kwok, James, Xie, Zeke
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914482893094912
author Shao, Shitong
Bai, Lichen
Wan, Pengfei
Kwok, James
Xie, Zeke
author_facet Shao, Shitong
Bai, Lichen
Wan, Pengfei
Kwok, James
Xie, Zeke
contents Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis compounds computation across spatial-temporal token growth and iterative denoising, making attention and memory traffic major bottlenecks in real-world settings. This survey provides a systematic and deployment-oriented review of efficient video diffusion models. We propose a unified categorization that organizes existing methods into four classes of main paradigms, including step distillation, efficient attention, model compression, and cache/trajectory optimization. Building on this categorization, we respectively analyze algorithmic trends of these four paradigms and examine how different design choices target two core objectives: reducing the number of function evaluations and minimizing per-step overhead. Finally, we discuss open challenges and future directions, including quality preservation under composite acceleration, hardware-software co-design, robust real-time long-horizon generation, and open infrastructure for standardized evaluation. To the best of our knowledge, our work is the first comprehensive survey on efficient video diffusion models, offering researchers and engineers a structured overview of the field and its emerging research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15911
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Video Diffusion Models: Advancements and Challenges
Shao, Shitong
Bai, Lichen
Wan, Pengfei
Kwok, James
Xie, Zeke
Computer Vision and Pattern Recognition
Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis compounds computation across spatial-temporal token growth and iterative denoising, making attention and memory traffic major bottlenecks in real-world settings. This survey provides a systematic and deployment-oriented review of efficient video diffusion models. We propose a unified categorization that organizes existing methods into four classes of main paradigms, including step distillation, efficient attention, model compression, and cache/trajectory optimization. Building on this categorization, we respectively analyze algorithmic trends of these four paradigms and examine how different design choices target two core objectives: reducing the number of function evaluations and minimizing per-step overhead. Finally, we discuss open challenges and future directions, including quality preservation under composite acceleration, hardware-software co-design, robust real-time long-horizon generation, and open infrastructure for standardized evaluation. To the best of our knowledge, our work is the first comprehensive survey on efficient video diffusion models, offering researchers and engineers a structured overview of the field and its emerging research directions.
title Efficient Video Diffusion Models: Advancements and Challenges
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.15911