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

TL;DR

MoTDiff introduces a novel high-resolution motion trajectory estimation framework from a single blurred image using diffusion models, significantly improving the quality and accuracy of motion information extraction in imaging applications.

Contribution

It is the first to utilize diffusion models for high-resolution motion trajectory estimation from a single blurred image, enhancing detail and precision over prior methods.

Findings

Outperforms state-of-the-art in blind deblurring

Effective in coded exposure photography

Produces high-quality, fine-grained motion trajectories

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.