UOD: Unseen Object Detection in 3D Point Cloud
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912396258312192 |
|---|---|
| author | Choi, Hyunjun Um, Daeho Jeong, Hawook |
| author_facet | Choi, Hyunjun Um, Daeho Jeong, Hawook |
| contents | Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical methods to enhance the performance of 3D detection and Out-Of-Distribution (OOD) classification for unseen objects. The proposed methods include anomaly sample augmentation, learning of universal objectness, learning of detecting unseen objects, and learning of distinguishing unseen objects. To demonstrate the effectiveness of our approach, we propose the KITTI Misc benchmark and two additional synthetic OOD benchmarks: the Nuscenes OOD benchmark and the SUN-RGBD OOD benchmark. The proposed methods consistently enhance performance by a large margin across all existing methods, giving insight for future work on unseen 3D object detection in the wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03846 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UOD: Unseen Object Detection in 3D Point Cloud Choi, Hyunjun Um, Daeho Jeong, Hawook Computer Vision and Pattern Recognition Machine Learning Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical methods to enhance the performance of 3D detection and Out-Of-Distribution (OOD) classification for unseen objects. The proposed methods include anomaly sample augmentation, learning of universal objectness, learning of detecting unseen objects, and learning of distinguishing unseen objects. To demonstrate the effectiveness of our approach, we propose the KITTI Misc benchmark and two additional synthetic OOD benchmarks: the Nuscenes OOD benchmark and the SUN-RGBD OOD benchmark. The proposed methods consistently enhance performance by a large margin across all existing methods, giving insight for future work on unseen 3D object detection in the wild. |
| title | UOD: Unseen Object Detection in 3D Point Cloud |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.03846 |