Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation
Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a novel unified framework which decomposes the detection problem into a structured polygon prediction task and a depth recovery task. Different from the widely studied 2D bounding boxes, the proposed novel structured polygon in the 2D image consists of several projected surfaces of the target object. Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection. In order to inversely project the predicted 2D structured polygon to a cuboid in the 3D physical world, the following depth recovery task uses the object height prior to complete the inverse projection transformation with the given camera projection matrix. Moreover, a fine-grained 3D box refinement scheme is proposed to further rectify the 3D detection results. Experiments are conducted on the challenging KITTI benchmark, in which our method achieves state-of-the-art detection accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionDepth EstimationMonocular 3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detection
Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images. A subset of viewpoint-agnostic monocular 3D detection methods also do not explicitly leverage scene hom…
3D Object DetectionMonocular 3D Object Detectionobject-detectionObject Detection+1Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection
We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth su…
3D Object DetectionMonocular 3D Object Detectionobject-detectionObject Detection+1DPPD: Deformable Polar Polygon Object Detection
Regular object detection methods output rectangle bounding boxes, which are unable to accurately describe the actual object shapes. Instance segmentation methods output pixel-level labels, which are computationally expen…
Autonomous DrivingInstance SegmentationObjectobject-detection+2IROAM: Improving Roadside Monocular 3D Object Detection Learning from Autonomous Vehicle Data Domain
In autonomous driving, The perception capabilities of the ego-vehicle can be improved with roadside sensors, which can provide a holistic view of the environment. However, existing monocular detection methods designed fo…
3D Object DetectionAutonomous DrivingContrastive LearningMonocular 3D Object Detection+2MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors
Perspective projection has been extensively utilized in monocular 3D object detection methods. It introduces geometric priors from 2D bounding boxes and 3D object dimensions to reduce the uncertainty of depth estimation.…
3D Object DetectionDepth EstimationDepth PredictionMonocular 3D Object Detection+3