paper-with-me

홈 › Papers

Exploring Geometric Consistency for Monocular 3D Object Detection

2021-04-12 · CVPR 2022 1 · Qing Lian, Botao Ye, Ruijia Xu, Weilong Yao, Tong Zhang

This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal how existing methods fail to consistently localize objects when different geometric shifts occur. In particular, we design a series of geometric manipulations to diagnose existing detectors and then illustrate their vulnerability to consistently associate the depth with object apparent sizes and positions. To alleviate this issue, we propose four geometry-aware data augmentation approaches to enhance the geometric consistency of the detectors. We first modify some commonly used data augmentation methods for 2D images so that they can maintain geometric consistency in 3D spaces. We demonstrate such modifications are important. In addition, we propose a 3D-specific image perturbation method that employs the camera movement. During the augmentation process, the camera system with the corresponding image is manipulated, while the geometric visual cues for depth recovery are preserved. We show that by using the geometric consistency constraints, the proposed augmentation techniques lead to improvements on the KITTI and nuScenes monocular 3D detection benchmarks with state-of-the-art results. In addition, we demonstrate that the augmentation methods are well suited for semi-supervised training and cross-dataset generalization.

📄 PDF Abstract BibTeX arXiv:2104.05858

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionAutonomous DrivingData AugmentationDepth EstimationMonocular 3D Object DetectionObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Monocular 3D Object Detection via Geometric Reasoning on Keypoints

2019-05-14 · Ivan Barabanau, Alexey Artemov, Evgeny Burnaev, Vyacheslav Murashkin

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates,…

3D Object DetectionKeypoint DetectionMonocular 3D Object DetectionObject+2

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 DetectionAutonomous Driving

Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints

2019-05-23 · Andretti Naiden, Vlad Paunescu, Gyeongmo Kim, ByeongMoon Jeon 외

We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and co…

3D Object DetectionDeep LearningDepth EstimationForm+4

GOOD: Exploring Geometric Cues for Detecting Objects in an Open World

2022-12-22 · Haiwen Huang, Andreas Geiger, Dan Zhang

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitt…

Class-agnostic Object DetectionObjectobject-detectionObject Detection+1

MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label

2026-04-02 · Junyoung Jung, Seokwon Kim, Jung Uk Kim arxiv

Monocular 3D object detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely anno…

Monocular 3D Object Detection