Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models

Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions in the 2D space, and videos as a sequence of continuous warpi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Daras, Giannis, Nie, Weili, Kreis, Karsten, Dimakis, Alex, Mardani, Morteza, Kovachki, Nikola Borislavov, Vahdat, Arash
Format: Article
Language:English
Subjects:
Continuity (mathematics)
Frames (data processing)
Function space
Inverse problems
Transformations (mathematics)
Video
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions in the 2D space, and videos as a sequence of continuous warping transformations between different frames. This perspective allows us to train function space diffusion models only on images and utilize them to solve temporally correlated inverse problems. The function space diffusion models need to be equivariant with respect to the underlying spatial transformations. To ensure temporal consistency, we introduce a simple post-hoc test-time guidance towards (self)-equivariant solutions. Our method allows us to deploy state-of-the-art latent diffusion models such as Stable Diffusion XL to solve video inverse problems. We demonstrate the effectiveness of our method for video inpainting and \(8\times\) video super-resolution, outperforming existing techniques based on noise transformations. We provide generated video results: https://giannisdaras.github.io/warped_diffusion.github.io/.
ISSN:2331-8422