English

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

Computer Vision and Pattern Recognition 2025-10-31 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2510.26173,
  title  = {MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models},
  author = {Wontae Choi and Jaelin Lee and Hyung Sup Yun and Byeungwoo Jeon and Il Yong Chun},
  journal= {arXiv preprint arXiv:2510.26173},
  year   = {2025}
}

Comments

10 pages, 6 figures

R2 v1 2026-07-01T07:13:16.063Z