Towards Closing the Domain Gap with Event Cameras
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918254615724032 |
|---|---|
| author | Sevinc, M. Oltan Wu, Liao Cruz, Francisco |
| author_facet | Sevinc, M. Oltan Wu, Liao Cruz, Francisco |
| contents | Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16178 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Closing the Domain Gap with Event Cameras Sevinc, M. Oltan Wu, Liao Cruz, Francisco Computer Vision and Pattern Recognition Artificial Intelligence Robotics Although traditional cameras are the primary sensor for end-to-end driving, their performance suffers greatly when the conditions of the data they were trained on does not match the deployment environment, a problem known as the domain gap. In this work, we consider the day-night lighting difference domain gap. Instead of traditional cameras we propose event cameras as a potential alternative which can maintain performance across lighting condition domain gaps without requiring additional adjustments. Our results show that event cameras maintain more consistent performance across lighting conditions, exhibiting domain-shift penalties that are generally comparable to or smaller than grayscale frames and provide superior baseline performance in cross-domain scenarios. |
| title | Towards Closing the Domain Gap with Event Cameras |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2512.16178 |