EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908933804785664 |
|---|---|
| author | Bartolomei, Luca Tosi, Fabio Poggi, Matteo Mattoccia, Stefano Gallego, Guillermo |
| author_facet | Bartolomei, Luca Tosi, Fabio Poggi, Matteo Mattoccia, Stefano Gallego, Guillermo |
| contents | We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images. From these images, we derive either proxy annotations and proxy events through state-of-the-art novel view synthesis techniques, or simply proxy annotations when images are already paired with event data. Using the training set generated by our data factory, we repurpose state-of-the-art stereo models from RGB literature to process event data, obtaining new event stereo models with unprecedented generalization capabilities. Experiments on widely used event stereo datasets support the effectiveness of EventHub and show how the same data distillation mechanism can improve the accuracy of RGB stereo foundation models in challenging conditions such as nighttime scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02331 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors Bartolomei, Luca Tosi, Fabio Poggi, Matteo Mattoccia, Stefano Gallego, Guillermo Computer Vision and Pattern Recognition We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images. From these images, we derive either proxy annotations and proxy events through state-of-the-art novel view synthesis techniques, or simply proxy annotations when images are already paired with event data. Using the training set generated by our data factory, we repurpose state-of-the-art stereo models from RGB literature to process event data, obtaining new event stereo models with unprecedented generalization capabilities. Experiments on widely used event stereo datasets support the effectiveness of EventHub and show how the same data distillation mechanism can improve the accuracy of RGB stereo foundation models in challenging conditions such as nighttime scenes. |
| title | EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02331 |