MonoGRNet: A General Framework for Monocular 3D Object Detection

2021-04-18 · Zengyi Qin, Jinglu Wang, Yan Lu

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet decomposes the monocular 3D object detection task into four sub-tasks including 2D object detection, instance-level depth estimation, projected 3D center estimation and local corner regression. The task decomposition significantly facilitates the monocular 3D object detection, allowing the target 3D bounding boxes to be efficiently predicted in a single forward pass, without using object proposals, post-processing or the computationally expensive pixel-level depth estimation utilized by previous methods. In addition, MonoGRNet flexibly adapts to both fully and weakly supervised learning, which improves the feasibility of our framework in diverse settings. Experiments are conducted on KITTI, Cityscapes and MS COCO datasets. Results demonstrate the promising performance of our framework in various scenarios.

📄 PDF Abstract BibTeX arXiv:2104.08797

Code (0)

등록된 구현이 없습니다.

Tasks

2D Object Detection 3D Object Detection Depth Estimation Monocular 3D Object DetectionObjectobject-detection Object Detection Scene UnderstandingWeakly-supervised Learning

MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

2018-11-26 · Zengyi Qin, Jinglu Wang, Yan Lu

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery pro…

2D Object Detection 3D Object Detection Depth Estimation Monocular 3D Object Detection+5

Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training

2023-10-02 · Fulong Ma, Xiaoyang Yan, Guoyang Zhao, Xiaojie Xu 외

Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datas…

3D Object Detection Autonomous Driving Monocular 3D Object Detection object-detection+1

MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient

2023-10-17 · Sen Wang, Jin Zheng

Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image. Existing monocular 3D detection knowledge distillation methods usually proje…

3D Object Detection GPU Knowledge Distillation Monocular 3D Object Detection+2

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

2021-06-02 · Danila Rukhovich, Anna Vorontsova, Anton Konushin

In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object dete…

3D Object Detection Monocular 3D Object Detection Monocular 3D Object Detection (10 / NYU-37)Monocular 3D Object Detection (10 / PNet-30)+4

MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection

2025-11-11 · Sunghun Yang, Minhyeok Lee, Jungho Lee, Sangyoun Lee arxiv

Monocular 3D object detection offers a cost-effective solution for autonomous driving but suffers from ill-posed depth and limited field of view. These constraints cause a lack of geometric cues and reduced accuracy in o…

Monocular 3D Object Detection Autonomous Driving