paper-with-me

Papers

ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection

2021-11-28 · Aqi Gao, Yanwei Pang, Jing Nie, Jiale Cao, Yishun Guo

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.

📄 PDF Abstract BibTeX arXiv:2111.14055

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionKnowledge Distillationobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Stereo R-CNN based 3D Object Detection for Autonomous Driving

2019-02-26 · CVPR 2019 6 · Peiliang Li, Xiaozhi Chen, Shaojie Shen

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+3

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

2021-08-18 · ICCV 2021 10 · Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li

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 Matching

ESGNN: Towards Equivariant Scene Graph Neural Network for 3D Scene Understanding

2024-06-30 · Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo, Truong Do 외

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 Understanding

TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding

2024-11-15 · Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo, Dezhen Song 외

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 Understanding

DSGN: Deep Stereo Geometry Network for 3D Object Detection

2020-01-10 · CVPR 2020 6 · Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia

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