MCFormer: A Multi-Cost-Volume Network and Comprehensive Benchmark for Particle Image Velocimetry

TL;DR

This paper introduces a large-scale synthetic PIV benchmark dataset and a novel deep learning architecture, MCFormer, which together enable standardized evaluation and significantly improved performance in particle image velocimetry tasks.

Contribution

The paper presents the first comprehensive PIV benchmark dataset and a specialized deep network, MCFormer, tailored for PIV, advancing evaluation standards and performance in the field.

Findings

MCFormer outperforms existing PIV methods with lowest NEPE

Benchmark dataset covers diverse flow conditions and particle densities

Significant performance variation observed among optical flow models

Abstract

Particle Image Velocimetry (PIV) is fundamental to fluid dynamics, yet deep learning applications face significant hurdles. A critical gap exists: the lack of comprehensive evaluation of how diverse optical flow models perform specifically on PIV data, largely due to limitations in available datasets and the absence of a standardized benchmark. This prevents fair comparison and hinders progress. To address this, our primary contribution is a novel, large-scale synthetic PIV benchmark dataset generated from diverse CFD simulations (JHTDB and Blasius). It features unprecedented variety in particle densities, flow velocities, and continuous motion, enabling, for the first time, a standardized and rigorous evaluation of various optical flow and PIV algorithms. Complementing this, we propose Multi Cost Volume PIV (MCFormer), a new deep network architecture leveraging multi-frame temporal information and multiple cost volumes, specifically designed for PIV's sparse nature. Our comprehensive benchmark evaluation, the first of its kind, reveals significant performance variations among adapted optical flow models and demonstrates that MCFormer significantly outperforms existing methods, achieving the lowest overall normalized endpoint error (NEPE). This work provides both a foundational benchmark resource essential for future PIV research and a state-of-the-art method tailored for PIV challenges. We make our benchmark dataset and code publicly available to foster future research in this area.