Event6D: Event-based Novel Object 6D Pose Tracking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910104678301696 |
|---|---|
| author | Kang, Jae-Young Cho, Hoonhee Lee, Taeyeop Kang, Minjun Wen, Bowen Kim, Youngho Yoon, Kuk-Jin |
| author_facet | Kang, Jae-Young Cho, Hoonhee Lee, Taeyeop Kang, Minjun Wen, Bowen Kim, Youngho Yoon, Kuk-Jin |
| contents | Event cameras provide microsecond latency, making them suitable for 6D object pose tracking in fast, dynamic scenes where conventional RGB and depth pipelines suffer from motion blur and large pixel displacements. We introduce EventTrack6D, an event-depth tracking framework that generalizes to novel objects without object-specific training by reconstructing both intensity and depth at arbitrary timestamps between depth frames. Conditioned on the most recent depth measurement, our dual reconstruction recovers dense photometric and geometric cues from sparse event streams. Our EventTrack6D operates at over 120 FPS and maintains temporal consistency under rapid motion. To support training and evaluation, we introduce a comprehensive benchmark suite: a large-scale synthetic dataset for training and two complementary evaluation sets, including real and simulated event datasets. Trained exclusively on synthetic data, EventTrack6D generalizes effectively to real-world scenarios without fine-tuning, maintaining accurate tracking across diverse objects and motion patterns. Our method and datasets validate the effectiveness of event cameras for event-based 6D pose tracking of novel objects. Code and datasets are publicly available at https://chohoonhee.github.io/Event6D. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28045 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Event6D: Event-based Novel Object 6D Pose Tracking Kang, Jae-Young Cho, Hoonhee Lee, Taeyeop Kang, Minjun Wen, Bowen Kim, Youngho Yoon, Kuk-Jin Computer Vision and Pattern Recognition Event cameras provide microsecond latency, making them suitable for 6D object pose tracking in fast, dynamic scenes where conventional RGB and depth pipelines suffer from motion blur and large pixel displacements. We introduce EventTrack6D, an event-depth tracking framework that generalizes to novel objects without object-specific training by reconstructing both intensity and depth at arbitrary timestamps between depth frames. Conditioned on the most recent depth measurement, our dual reconstruction recovers dense photometric and geometric cues from sparse event streams. Our EventTrack6D operates at over 120 FPS and maintains temporal consistency under rapid motion. To support training and evaluation, we introduce a comprehensive benchmark suite: a large-scale synthetic dataset for training and two complementary evaluation sets, including real and simulated event datasets. Trained exclusively on synthetic data, EventTrack6D generalizes effectively to real-world scenarios without fine-tuning, maintaining accurate tracking across diverse objects and motion patterns. Our method and datasets validate the effectiveness of event cameras for event-based 6D pose tracking of novel objects. Code and datasets are publicly available at https://chohoonhee.github.io/Event6D. |
| title | Event6D: Event-based Novel Object 6D Pose Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.28045 |