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

2025-12-22

AI Summary

This work addresses the problem of temporal dynamic reconstruction from a single motion-blurred image. We propose the first cross-temporal (past/present/future) joint generation framework leveraging an internet-scale pre-trained video diffusion model. Our method eschews handcrafted priors, instead implicitly modeling blur kernels and explicitly enforcing spatiotemporal consistency constraints to transfer video diffusion priors into the blur domain—enabling multi-frame-consistent restoration without paired training data. Unlike conventional deblurring or unidirectional prediction approaches, ours is the first to directly synthesize physically plausible, temporally coherent video sequences spanning multiple time instants from a single blurred input. Extensive evaluation on real-world complex motion-blurred images demonstrates significant improvements over state-of-the-art methods. Moreover, the reconstructed sequences effectively support downstream tasks including camera trajectory estimation, object motion analysis, and dynamic 3D reconstruction.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Temporal Planning
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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

Problem

• Recovering complex scene dynamics from motion-blurred images
• Predicting past and future events beyond the captured moment
• Leveraging large-scale video priors for robust inverse problem solving

Innovation

• Uses pre-trained video diffusion model
• Recovers past, present, future scene dynamics
• Generalizes to challenging real-world images