EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914138701168640 |
|---|---|
| author | Macaulay, Sadiq Layi Kaygusuz, Nimet Hadfield, Simon |
| author_facet | Macaulay, Sadiq Layi Kaygusuz, Nimet Hadfield, Simon |
| contents | Event cameras, with their high dynamic range (HDR) and low latency, offer a promising alternative for robust depth estimation in challenging environments. However, many event-based depth estimation approaches are constrained by small-scale annotated datasets, limiting their generalizability to real-world scenarios. To bridge this gap, we introduce EvtSlowTV, a large-scale event camera dataset curated from publicly available YouTube footage, which contains more than 13B events across various environmental conditions and motions, including seasonal hiking, flying, scenic driving, and underwater exploration. EvtSlowTV is an order of magnitude larger than existing event datasets, providing an unconstrained, naturalistic setting for event-based depth learning. This work shows the suitability of EvtSlowTV for a self-supervised learning framework to capitalise on the HDR potential of raw event streams. We further demonstrate that training with EvtSlowTV enhances the model's ability to generalise to complex scenes and motions. Our approach removes the need for frame-based annotations and preserves the asynchronous nature of event data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimation Macaulay, Sadiq Layi Kaygusuz, Nimet Hadfield, Simon Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics Event cameras, with their high dynamic range (HDR) and low latency, offer a promising alternative for robust depth estimation in challenging environments. However, many event-based depth estimation approaches are constrained by small-scale annotated datasets, limiting their generalizability to real-world scenarios. To bridge this gap, we introduce EvtSlowTV, a large-scale event camera dataset curated from publicly available YouTube footage, which contains more than 13B events across various environmental conditions and motions, including seasonal hiking, flying, scenic driving, and underwater exploration. EvtSlowTV is an order of magnitude larger than existing event datasets, providing an unconstrained, naturalistic setting for event-based depth learning. This work shows the suitability of EvtSlowTV for a self-supervised learning framework to capitalise on the HDR potential of raw event streams. We further demonstrate that training with EvtSlowTV enhances the model's ability to generalise to complex scenes and motions. Our approach removes the need for frame-based annotations and preserves the asynchronous nature of event data. |
| title | EvtSlowTV -- A Large and Diverse Dataset for Event-Based Depth Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2511.02953 |