FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911737772507136 |
|---|---|
| author | Safadoust, Sadra Tosi, Fabio Poggi, Matteo Güney, Fatma |
| author_facet | Safadoust, Sadra Tosi, Fabio Poggi, Matteo Güney, Fatma |
| contents | We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a hierarchical transformer architecture that captures extensive global context, enabling the model to effectively model long-range correspondences. To overcome the limitations of localized matching, we formulate the flow initialization as an optimal transport problem. This formulation yields a highly robust initial flow field, alongside explicitly derived occlusion and confidence maps. These cues are then seamlessly integrated into a guided refinement stage, where the network actively propagates reliable motion estimates from high-confidence regions into ambiguous, low-confidence areas. Extensive experiments across the Sintel, KITTI, Spring, and LayeredFlow datasets validate the effectiveness of our approach. FlowIt achieves state-of-the-art results on the competitive Sintel benchmark and establishes new state-of-the-art cross-dataset zero-shot generalization performance on Sintel, Spring, and LayeredFlow, while also delivering competitive performance on both the KITTI benchmark and KITTI zero-shot generalization settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28759 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow Safadoust, Sadra Tosi, Fabio Poggi, Matteo Güney, Fatma Computer Vision and Pattern Recognition We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a hierarchical transformer architecture that captures extensive global context, enabling the model to effectively model long-range correspondences. To overcome the limitations of localized matching, we formulate the flow initialization as an optimal transport problem. This formulation yields a highly robust initial flow field, alongside explicitly derived occlusion and confidence maps. These cues are then seamlessly integrated into a guided refinement stage, where the network actively propagates reliable motion estimates from high-confidence regions into ambiguous, low-confidence areas. Extensive experiments across the Sintel, KITTI, Spring, and LayeredFlow datasets validate the effectiveness of our approach. FlowIt achieves state-of-the-art results on the competitive Sintel benchmark and establishes new state-of-the-art cross-dataset zero-shot generalization performance on Sintel, Spring, and LayeredFlow, while also delivering competitive performance on both the KITTI benchmark and KITTI zero-shot generalization settings. |
| title | FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.28759 |