Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss

TL;DR

This paper presents a self-supervised dual-frame fluid motion estimation method for 3D particle tracking velocimetry that outperforms supervised methods with minimal training data, using a novel zero-divergence loss and test-time optimization.

Contribution

The authors introduce a fully self-supervised dual-frame fluid motion estimation approach with a new zero-divergence loss and test-time optimization, requiring only 1% of labeled data and achieving cross-domain robustness.

Findings

Outperforms fully-supervised methods with only 1% labeled data.

Achieves strong cross-domain robustness through test-time optimization.

Introduces an efficient splat-based implementation of zero-divergence loss.

Abstract

3D particle tracking velocimetry (PTV) is a key technique for analyzing turbulent flow, one of the most challenging computational problems of our century. At the core of 3D PTV is the dual-frame fluid motion estimation algorithm, which tracks particles across two consecutive frames. Recently, deep learning-based methods have achieved impressive accuracy in dual-frame fluid motion estimation; however, they heavily depend on large volumes of labeled data. In this paper, we introduce a new method that is completely self-supervised and notably outperforms its fully-supervised counterparts while requiring only 1% of the training samples (without labels) used by previous methods. Our method features a novel zero-divergence loss that is specific to the domain of turbulent flow. Inspired by the success of splat operation in high-dimensional filtering and random fields, we propose a splat-based implementation for this loss which is both efficient and effective. The self-supervised nature of our method naturally supports test-time optimization, leading to the development of a tailored Dynamic Velocimetry Enhancer (DVE) module. We demonstrate that strong cross-domain robustness is achieved through test-time optimization on unseen leave-one-out synthetic domains and real physical/biological domains. Code, data and models are available at https://github.com/Forrest-110/FluidMotionNet.