Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917611170693120 |
|---|---|
| author | Liu, Feng Huang, Tengteng Zhang, Qianjing Yao, Haotian Zhang, Chi Wan, Fang Ye, Qixiang Zhou, Yanzhao |
| author_facet | Liu, Feng Huang, Tengteng Zhang, Qianjing Yao, Haotian Zhang, Chi Wan, Fang Ye, Qixiang Zhou, Yanzhao |
| contents | Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections. Our paper presents Ray Denoising, an innovative method that enhances detection accuracy by strategically sampling along camera rays to construct hard negative examples. These examples, visually challenging to differentiate from true positives, compel the model to learn depth-aware features, thereby improving its capacity to distinguish between true and false positives. Ray Denoising is designed as a plug-and-play module, compatible with any DETR-style multi-view 3D detectors, and it only minimally increases training computational costs without affecting inference speed. Our comprehensive experiments, including detailed ablation studies, consistently demonstrate that Ray Denoising outperforms strong baselines across multiple datasets. It achieves a 1.9\% improvement in mean Average Precision (mAP) over the state-of-the-art StreamPETR method on the NuScenes dataset. It shows significant performance gains on the Argoverse 2 dataset, highlighting its generalization capability. The code will be available at https://github.com/LiewFeng/RayDN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03634 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection Liu, Feng Huang, Tengteng Zhang, Qianjing Yao, Haotian Zhang, Chi Wan, Fang Ye, Qixiang Zhou, Yanzhao Computer Vision and Pattern Recognition Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections. Our paper presents Ray Denoising, an innovative method that enhances detection accuracy by strategically sampling along camera rays to construct hard negative examples. These examples, visually challenging to differentiate from true positives, compel the model to learn depth-aware features, thereby improving its capacity to distinguish between true and false positives. Ray Denoising is designed as a plug-and-play module, compatible with any DETR-style multi-view 3D detectors, and it only minimally increases training computational costs without affecting inference speed. Our comprehensive experiments, including detailed ablation studies, consistently demonstrate that Ray Denoising outperforms strong baselines across multiple datasets. It achieves a 1.9\% improvement in mean Average Precision (mAP) over the state-of-the-art StreamPETR method on the NuScenes dataset. It shows significant performance gains on the Argoverse 2 dataset, highlighting its generalization capability. The code will be available at https://github.com/LiewFeng/RayDN. |
| title | Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.03634 |