MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Wontae, Lee, Jaelin, Yun, Hyung Sup, Jeon, Byeungwoo, Chun, Il Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917050203504640
author Choi, Wontae
Lee, Jaelin
Yun, Hyung Sup
Jeon, Byeungwoo
Chun, Il Yong
author_facet Choi, Wontae
Lee, Jaelin
Yun, Hyung Sup
Jeon, Byeungwoo
Chun, Il Yong
contents Accurate estimation of motion information is crucial in diverse computational imaging and computer vision applications. Researchers have investigated various methods to extract motion information from a single blurred image, including blur kernels and optical flow. However, existing motion representations are often of low quality, i.e., coarse-grained and inaccurate. In this paper, we propose the first high-resolution (HR) Motion Trajectory estimation framework using Diffusion models (MoTDiff). Different from existing motion representations, we aim to estimate an HR motion trajectory with high-quality from a single motion-blurred image. The proposed MoTDiff consists of two key components: 1) a new conditional diffusion framework that uses multi-scale feature maps extracted from a single blurred image as a condition, and 2) a new training method that can promote precise identification of a fine-grained motion trajectory, consistent estimation of overall shape and position of a motion path, and pixel connectivity along a motion trajectory. Our experiments demonstrate that the proposed MoTDiff can outperform state-of-the-art methods in both blind image deblurring and coded exposure photography applications.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models
Choi, Wontae
Lee, Jaelin
Yun, Hyung Sup
Jeon, Byeungwoo
Chun, Il Yong
Computer Vision and Pattern Recognition
Accurate estimation of motion information is crucial in diverse computational imaging and computer vision applications. Researchers have investigated various methods to extract motion information from a single blurred image, including blur kernels and optical flow. However, existing motion representations are often of low quality, i.e., coarse-grained and inaccurate. In this paper, we propose the first high-resolution (HR) Motion Trajectory estimation framework using Diffusion models (MoTDiff). Different from existing motion representations, we aim to estimate an HR motion trajectory with high-quality from a single motion-blurred image. The proposed MoTDiff consists of two key components: 1) a new conditional diffusion framework that uses multi-scale feature maps extracted from a single blurred image as a condition, and 2) a new training method that can promote precise identification of a fine-grained motion trajectory, consistent estimation of overall shape and position of a motion path, and pixel connectivity along a motion trajectory. Our experiments demonstrate that the proposed MoTDiff can outperform state-of-the-art methods in both blind image deblurring and coded exposure photography applications.
title MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.26173