Shape-Aware Monocular 3D Object Detection
The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vulnerable to occluded and truncated objects. In this paper, a single-stage monocular 3D object detection model is proposed. An instance-segmentation head is integrated into the model training, which allows the model to be aware of the visible shape of a target object. The detection largely avoids interference from irrelevant regions surrounding the target objects. In addition, we also reveal that the popular IoU-based evaluation metrics, which were originally designed for evaluating stereo or LiDAR-based detection methods, are insensitive to the improvement of monocular 3D object detection algorithms. A novel evaluation metric, namely average depth similarity (ADS) is proposed for the monocular 3D object detection models. Our method outperforms the baseline on both the popular and the proposed evaluation metrics while maintaining real-time efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionInstance SegmentationMonocular 3D Object DetectionObjectobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection
Existing deep learning-based approaches for monocular 3D object detection in autonomous driving often model the object as a rotated 3D cuboid while the object's geometric shape has been ignored. In this work, we propose …
3D Object DetectionAutonomous DrivingMonocular 3D Object DetectionObject+2S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Recently, transformer-based methods have shown exceptional performance in monocular 3D object detection, which can predict 3D attributes from a single 2D image. These methods typically use visual and depth representation…
3D Object DetectionMonocular 3D Object Detectionobject-detectionObject DetectionMOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos
Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric ma…
BenchmarkingObjectObject LocalizationDimension Embeddings for Monocular 3D Object Detection
Most existing deep learning-based approaches for monocular 3D object detection directly regress the dimensions of objects and overlook their importance in solving the ill-posed problem. In this paper, we propose a ge…
3D Object DetectionMonocular 3D Object DetectionObjectobject-detection+1Monocular Differentiable Rendering for Self-Supervised 3D Object Detection
3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconst…
3D Object Detection3D Object Detection From Monocular Images3D Shape ReconstructionDepth Estimation+5