Scholarlink

<p>Monocular 3D object detection models have become increasingly popular due to its low cost and ease of deployment. It remains challenging because of limited depth estimation and dataset imbalance. To tackle this challenge, we propose a Spatiotemporally Consistent Pseudo-labels Module (SCPM) that aims to enhance the performance of monocular 3D object detection models. Our proposed method leverages spatiotemporal priors and data augmentation to generate reliable and temporally consistent pseudo-labels, effectively mitigating survivorship bias. In addition, we introduce a depth decoupling module guided by geometric priors to improve depth estimation and spatial localization, particularly under occlusion. The pro-posed framework enhances detection robustness and reduces missed detections. Extensive experiments conducted on the KITTI dataset demonstrate that our method significantly outperforms existing monocular 3D detection approaches, achieving state-of-the-art performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SCPM: monocular 3D object detection with spatiotemporal consistent pseudo-labels module

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月12日

查看全文
  • Yujing Wang,
  • Abdul Hadi Abd Rahman,
  • Fadilla Atyka Nor Rashid

摘要

Monocular 3D object detection models have become increasingly popular due to its low cost and ease of deployment. It remains challenging because of limited depth estimation and dataset imbalance. To tackle this challenge, we propose a Spatiotemporally Consistent Pseudo-labels Module (SCPM) that aims to enhance the performance of monocular 3D object detection models. Our proposed method leverages spatiotemporal priors and data augmentation to generate reliable and temporally consistent pseudo-labels, effectively mitigating survivorship bias. In addition, we introduce a depth decoupling module guided by geometric priors to improve depth estimation and spatial localization, particularly under occlusion. The pro-posed framework enhances detection robustness and reduces missed detections. Extensive experiments conducted on the KITTI dataset demonstrate that our method significantly outperforms existing monocular 3D detection approaches, achieving state-of-the-art performance.