Bridging the Gap: A Real-World Dataset and Evaluation of Optical Flow Models in Large Displacement Scenarios

Bachelor Thesis (2025)
Author(s)

M. Timmerije (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Jan Gemert – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

A.S. Gielisse – Mentor (TU Delft - Pattern Recognition and Bioinformatics)

Alexios Voulimeneas – Graduation committee member (TU Delft - Cyber Security)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
27-06-2025
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
[':']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Optical flow models excel on synthetic benchmarks but can struggle with real-world scenarios involving large displacements, which are critical for applications like autonomous navigation and augmented reality. To address this, we introduce a novel real-world dataset and evaluation framework, using a specialized annotation tool to capture ground truth optical flow in scenarios with fast movements and close-range objects. Our approach minimizes confounders, providing clear insights into model performance with large displacements. Findings show recent models outperform the previous state-of-the-art, RAFT, across all tested scenarios. Both the annotation tool and dataset are available to support further research.

Files

License info not available