Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Chenyu, Yan, Shuo, Chen, Yixuan, Wang, Yujiang, Dong, Mingzhi, Yang, Xiaochen, Li, Dongsheng, Dick, Robert P., Lv, Qin, Yang, Fan, Lu, Tun, Gu, Ning, Shang, Li
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.12532
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912034787950592
author Wang, Chenyu
Yan, Shuo
Chen, Yixuan
Wang, Yujiang
Dong, Mingzhi
Yang, Xiaochen
Li, Dongsheng
Dick, Robert P.
Lv, Qin
Yang, Fan
Lu, Tun
Gu, Ning
Shang, Li
author_facet Wang, Chenyu
Yan, Shuo
Chen, Yixuan
Wang, Yujiang
Dong, Mingzhi
Yang, Xiaochen
Li, Dongsheng
Dick, Robert P.
Lv, Qin
Yang, Fan
Lu, Tun
Gu, Ning
Shang, Li
contents 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. Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Following this observation, Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions, eliminating massive computational redundancy in frame-wise diffusion models. The more sensitive and fine-grained noises are still acquired via later denoising steps, which can be essential to retain visual qualities. As such, deciding which intermediate steps should switch from motion-based propagations to denoising can be a crucial problem and a key tradeoff between efficiency and quality. Dr. Mo employs a meta-network named Denoising Step Selector (DSS) to dynamically determine desirable intermediate steps across video frames. Extensive evaluations on video generation and editing tasks have shown that Dr. Mo can substantially accelerate diffusion models in video tasks with improved visual qualities.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12532
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
Wang, Chenyu
Yan, Shuo
Chen, Yixuan
Wang, Yujiang
Dong, Mingzhi
Yang, Xiaochen
Li, Dongsheng
Dick, Robert P.
Lv, Qin
Yang, Fan
Lu, Tun
Gu, Ning
Shang, Li
Computer Vision and Pattern Recognition
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. Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Following this observation, Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions, eliminating massive computational redundancy in frame-wise diffusion models. The more sensitive and fine-grained noises are still acquired via later denoising steps, which can be essential to retain visual qualities. As such, deciding which intermediate steps should switch from motion-based propagations to denoising can be a crucial problem and a key tradeoff between efficiency and quality. Dr. Mo employs a meta-network named Denoising Step Selector (DSS) to dynamically determine desirable intermediate steps across video frames. Extensive evaluations on video generation and editing tasks have shown that Dr. Mo can substantially accelerate diffusion models in video tasks with improved visual qualities.
title Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.12532