FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
Abstract
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.
Cite
Text
Poggi and Tosi. "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases." International Conference on Computer Vision, 2025.Markdown
[Poggi and Tosi. "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/poggi2025iccv-flowseek/)BibTeX
@inproceedings{poggi2025iccv-flowseek,
title = {{FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases}},
author = {Poggi, Matteo and Tosi, Fabio},
booktitle = {International Conference on Computer Vision},
year = {2025},
pages = {5667-5679},
url = {https://mlanthology.org/iccv/2025/poggi2025iccv-flowseek/}
}