MoViE: Mobile Diffusion for Video Editing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Karjauv, Adil, Fathima, Noor, Lelekas, Ioannis, Porikli, Fatih, Ghodrati, Amir, Habibian, Amirhossein
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917863006142464
author Karjauv, Adil
Fathima, Noor
Lelekas, Ioannis
Porikli, Fatih
Ghodrati, Amir
Habibian, Amirhossein
author_facet Karjauv, Adil
Fathima, Noor
Lelekas, Ioannis
Porikli, Fatih
Ghodrati, Amir
Habibian, Amirhossein
contents Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods remain prohibitively expensive and challenging to deploy on mobile devices. In this study, we introduce a series of optimizations that render mobile video editing feasible. Building upon the existing image editing model, we first optimize its architecture and incorporate a lightweight autoencoder. Subsequently, we extend classifier-free guidance distillation to multiple modalities, resulting in a threefold on-device speedup. Finally, we reduce the number of sampling steps to one by introducing a novel adversarial distillation scheme which preserves the controllability of the editing process. Collectively, these optimizations enable video editing at 12 frames per second on mobile devices, while maintaining high quality. Our results are available at https://qualcomm-ai-research.github.io/mobile-video-editing/
format Preprint
id arxiv_https___arxiv_org_abs_2412_06578
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MoViE: Mobile Diffusion for Video Editing
Karjauv, Adil
Fathima, Noor
Lelekas, Ioannis
Porikli, Fatih
Ghodrati, Amir
Habibian, Amirhossein
Computer Vision and Pattern Recognition
Recent progress in diffusion-based video editing has shown remarkable potential for practical applications. However, these methods remain prohibitively expensive and challenging to deploy on mobile devices. In this study, we introduce a series of optimizations that render mobile video editing feasible. Building upon the existing image editing model, we first optimize its architecture and incorporate a lightweight autoencoder. Subsequently, we extend classifier-free guidance distillation to multiple modalities, resulting in a threefold on-device speedup. Finally, we reduce the number of sampling steps to one by introducing a novel adversarial distillation scheme which preserves the controllability of the editing process. Collectively, these optimizations enable video editing at 12 frames per second on mobile devices, while maintaining high quality. Our results are available at https://qualcomm-ai-research.github.io/mobile-video-editing/
title MoViE: Mobile Diffusion for Video Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06578