We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cross-dataset generalization on Sintel Final and KITTI, with a relative improvement of 10 and 15% over the previous state-of-the-art SEA-RAFT, as well as on Spring and LayeredFlow datasets.
@article{arxiv.2509.05297,
title = {FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases},
author = {Matteo Poggi and Fabio Tosi},
journal= {arXiv preprint arXiv:2509.05297},
year = {2025}
}