# Reliable Evaluation of MRI Motion Correction: Dataset and Insights

arXiv: https://arxiv.org/abs/2506.05975 · HTML: https://mlsanity.com/paper/2506.05975/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2025.

## Built on by (most cited first, 1 of 1)

- [MotionDPS: Motion-Compensated 3D Brain MRI Reconstruction](https://mlsanity.com/paper/2605.22121/) (2026)

## Abstract (arXiv)

Correcting motion artifacts in MRI is important, as they can hinder accurate diagnosis. However, evaluating deep learning-based and classical motion correction methods remains fundamentally difficult due to the lack of accessible ground-truth target data. To address this challenge, we study three evaluation approaches: real-world evaluation based on reference scans, simulated motion, and reference-free evaluation, each with its merits and shortcomings. To enable evaluation with real-world motion artifacts, we release PMoC3D, a dataset consisting of unprocessed Paired Motion-Corrupted 3D brain MRI data. To advance evaluation quality, we introduce MoMRISim, a feature-space metric trained for evaluating motion reconstructions. We assess each evaluation approach and find real-world evaluation together with MoMRISim, while not perfect, to be most reliable. Evaluation based on simulated motion systematically exaggerates algorithm performance, and reference-free evaluation overrates oversmoothed deep learning outputs.