Generating the Past, Present and Future from a Motion-Blurred Image

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tedla, SaiKiran, Zhu, Kelly, Canham, Trevor, Taubner, Felix, Brown, Michael S., Kutulakos, Kiriakos N., Lindell, David B.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908728767283200
author Tedla, SaiKiran
Zhu, Kelly
Canham, Trevor
Taubner, Felix
Brown, Michael S.
Kutulakos, Kiriakos N.
Lindell, David B.
author_facet Tedla, SaiKiran
Zhu, Kelly
Canham, Trevor
Taubner, Felix
Brown, Michael S.
Kutulakos, Kiriakos N.
Lindell, David B.
contents We seek to answer the question: what can a motion-blurred image reveal about a scene's past, present, and future? Although motion blur obscures image details and degrades visual quality, it also encodes information about scene and camera motion during an exposure. Previous techniques leverage this information to estimate a sharp image from an input blurry one, or to predict a sequence of video frames showing what might have occurred at the moment of image capture. However, they rely on handcrafted priors or network architectures to resolve ambiguities in this inverse problem, and do not incorporate image and video priors on large-scale datasets. As such, existing methods struggle to reproduce complex scene dynamics and do not attempt to recover what occurred before or after an image was taken. Here, we introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets to recover videos revealing complex scene dynamics during the moment of capture and what might have occurred immediately into the past or future. Our approach is robust and versatile; it outperforms previous methods for this task, generalizes to challenging in-the-wild images, and supports downstream tasks such as recovering camera trajectories, object motion, and dynamic 3D scene structure. Code and data are available at https://blur2vid.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2512_19817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating the Past, Present and Future from a Motion-Blurred Image
Tedla, SaiKiran
Zhu, Kelly
Canham, Trevor
Taubner, Felix
Brown, Michael S.
Kutulakos, Kiriakos N.
Lindell, David B.
Computer Vision and Pattern Recognition
Graphics
We seek to answer the question: what can a motion-blurred image reveal about a scene's past, present, and future? Although motion blur obscures image details and degrades visual quality, it also encodes information about scene and camera motion during an exposure. Previous techniques leverage this information to estimate a sharp image from an input blurry one, or to predict a sequence of video frames showing what might have occurred at the moment of image capture. However, they rely on handcrafted priors or network architectures to resolve ambiguities in this inverse problem, and do not incorporate image and video priors on large-scale datasets. As such, existing methods struggle to reproduce complex scene dynamics and do not attempt to recover what occurred before or after an image was taken. Here, we introduce a new technique that repurposes a pre-trained video diffusion model trained on internet-scale datasets to recover videos revealing complex scene dynamics during the moment of capture and what might have occurred immediately into the past or future. Our approach is robust and versatile; it outperforms previous methods for this task, generalizes to challenging in-the-wild images, and supports downstream tasks such as recovering camera trajectories, object motion, and dynamic 3D scene structure. Code and data are available at https://blur2vid.github.io
title Generating the Past, Present and Future from a Motion-Blurred Image
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2512.19817