FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918136429674496 |
|---|---|
| author | Poggi, Matteo Tosi, Fabio |
| author_facet | Poggi, Matteo Tosi, Fabio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05297 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases Poggi, Matteo Tosi, Fabio Computer Vision and Pattern Recognition 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. |
| title | FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.05297 |