WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913452585385984 |
|---|---|
| author | Zhou, Xingcheng Fu, Deyu Zimmer, Walter Liu, Mingyu Lakshminarasimhan, Venkatnarayanan Strand, Leah Knoll, Alois C. |
| author_facet | Zhou, Xingcheng Fu, Deyu Zimmer, Walter Liu, Mingyu Lakshminarasimhan, Venkatnarayanan Strand, Leah Knoll, Alois C. |
| contents | Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20818 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection Zhou, Xingcheng Fu, Deyu Zimmer, Walter Liu, Mingyu Lakshminarasimhan, Venkatnarayanan Strand, Leah Knoll, Alois C. Computer Vision and Pattern Recognition Existing roadside perception systems are limited by the absence of publicly available, large-scale, high-quality 3D datasets. Exploring the use of cost-effective, extensive synthetic datasets offers a viable solution to tackle this challenge and enhance the performance of roadside monocular 3D detection. In this study, we introduce the TUMTraf Synthetic Dataset, offering a diverse and substantial collection of high-quality 3D data to augment scarce real-world datasets. Besides, we present WARM-3D, a concise yet effective framework to aid the Sim2Real domain transfer for roadside monocular 3D detection. Our method leverages cheap synthetic datasets and 2D labels from an off-the-shelf 2D detector for weak supervision. We show that WARM-3D significantly enhances performance, achieving a +12.40% increase in mAP 3D over the baseline with only pseudo-2D supervision. With 2D GT as weak labels, WARM-3D even reaches performance close to the Oracle baseline. Moreover, WARM-3D improves the ability of 3D detectors to unseen sample recognition across various real-world environments, highlighting its potential for practical applications. |
| title | WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.20818 |