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 feature representation in 3D space. To solve this problem, we propose an efficient stereo geometry network (ESGN). The key in our ESGN is an efficient geometry-aware feature generation (EGFG) module. Our EGFG module first uses a stereo correlation and reprojection module to construct multi-scale stereo volumes in camera frustum space, second employs a multi-scale BEV projection and fusion module to generate multiple geometry-aware features. In these two steps, we adopt deep multi-scale information fusion for discriminative geometry-aware feature generation, without any complex aggregation networks. In addition, we introduce a deep geometry-aware feature distillation scheme to guide stereo feature learning with a LiDAR-based detector. The experiments are performed on the classical KITTI dataset. On KITTI test set, our ESGN outperforms the fast state-of-art-art detector YOLOStereo3D by 5.14\% on mAP$_{3d}$ at 62$ms$. To the best of our knowledge, our ESGN achieves a best trade-off between accuracy and speed. We hope that our efficient stereo geometry network can provide more possible directions for fast 3D object detection. Our source code will be released.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionKnowledge Distillationobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Stereo R-CNN based 3D Object Detection for Autonomous Driving
We propose a 3D object detection method for autonomous driving by fully exploiting the sparse and dense, semantic and geometry information in stereo imagery. Our method, called Stereo R-CNN, extends Faster R-CNN for ster…
3D Object Detection3D Object Detection From Stereo ImagesAutonomous DrivingObject+3LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector
Stereo-based 3D detection aims at detecting 3D object bounding boxes from stereo images using intermediate depth maps or implicit 3D geometry representations, which provides a low-cost solution for 3D perception. However…
3D geometry3D Object Detection From Stereo ImagesStereo MatchingESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding
Scene graphs have been proven to be useful for various scene understanding tasks due to their compact and explicit nature. However, existing approaches often neglect the importance of maintaining the symmetry-preserving …
Graph GenerationGraph Neural NetworkScene Graph GenerationScene UnderstandingTESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding
Scene graphs have proven to be highly effective for various scene understanding tasks due to their compact and explicit representation of relational information. However, current methods often overlook the critical impor…
Graph MatchingGraph Neural NetworkScene UnderstandingDSGN: Deep Stereo Geometry Network for 3D Object Detection
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods. It is caused by the way to form representation for the predict…
3D Object Detection3D Object Detection From Stereo ImagesObjectobject-detection+2