Monocular 3D Object Detection via Feature Domain Adaptation
Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches. In this paper, we propose a novel domain adaptation based monocular 3D object detection framework named DA-3Ddet, which adapts the feature from unsound image-based pseudo-LiDAR domain to the accurate real LiDAR domain for performance boosting. In order to solve the overlooked problem of inconsistency between the foreground mask of pseudo and real LiDAR caused by inaccurately estimated depth, we also introduce a context-aware foreground segmentation module which helps to involve relevant points for foreground masking. Extensive experiments on KITTI dataset demonstrate that our simple yet effective framework outperforms other state-of-the-arts by a large margin.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionDomain AdaptationForeground SegmentationMonocular 3D Object DetectionObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed propert…
3D Object DetectionAutonomous DrivingDepth EstimationDomain Adaptation+4Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection
Monocular 3D object detection is a low-cost but challenging task, as it requires generating accurate 3D localization solely from a single image input. Recent developed depth-assisted methods show promising results by usi…
3D Object DetectionDepth EstimationKnowledge DistillationMonocular 3D Object Detection+4MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly…
3D Object DetectionDepth EstimationDiversityDomain Adaptation+5Fully Test-Time Adaptation for Monocular 3D Object Detection
Monocular 3D object detection (Mono 3Det) aims to identify 3D objects from a single RGB image. However, existing methods often assume training and test data follow the same distribution, which may not hold in real-world …
3D Object DetectionMonocular 3D Object Detectionobject-detectionObject Detection+1Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training
Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. However, drastic performance degradation remains…
3D Object DetectionAutonomous DrivingDomain AdaptationMonocular 3D Object Detection+3