YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://github.com/Owen-Liuyuxuan/visualDet3D.
Code (2)
Tasks
3D Object Detection3D Object Detection From Stereo ImagesDisparity EstimationGPUObjectobject-detectionObject DetectionStereo MatchingSimilar Papers 제목 키워드 기반
ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection
Fast stereo based 3D object detectors have made great progress recently. However, they lag far behind high-precision stereo based methods in accuracy. We argue that the main reason is due to the poor geometry-aware featu…
3D Object DetectionKnowledge Distillationobject-detectionObject DetectionConfidence Guided Stereo 3D Object Detection with Split Depth Estimation
Accurate and reliable 3D object detection is vital to safe autonomous driving. Despite recent developments, the performance gap between stereo-based methods and LiDAR-based methods is still considerable. Accurate depth e…
3D Object Detection3D Object Detection From Stereo ImagesAutonomous DrivingDepth Estimation+3BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereo
Bounded by the inherent ambiguity of depth perception, contemporary multi-view 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is the …
3D Object DetectionDepth EstimationMotion Compensationobject-detection+1BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo
Bounded by the inherent ambiguity of depth perception, contemporary camera-based 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is th…
3D Object DetectionDepth Estimationobject-detectionObject DetectionObject-Centric Stereo Matching for 3D Object Detection
Safe autonomous driving requires reliable 3D object detection-determining the 6 DoF pose and dimensions of objects of interest. Using stereo cameras to solve this task is a cost-effective alternative to the widely used L…
3D Object Detection3D Object Detection From Stereo ImagesAutonomous DrivingDisparity Estimation+5