4 Hits in 4.9 sec

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

Xiaoyang Guo, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li
2021 arXiv   pre-print
To solve the problem, we propose LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection  ...  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  ...  LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector  ... 
arXiv:2108.08258v1 fatcat:hz7ix7azmfbf3oli7mpay7jf3a

3D Object Detection for Autonomous Driving: A Survey [article]

Rui Qian, Xin Lai, Xirong Li
2022 arXiv   pre-print
Taking a quick glance at the progress we have made, we attribute challenges to visual appearance recovery in the absence of depth information from images, representation learning from partially occluded  ...  Despite existing efforts, 3D object detection for autonomous driving is still in its infancy. Recently, a large body of literature have been investigated to address this 3D vision task.  ...  LIGA-Stereo [72] turns to real LiDAR signals for the high-level geometry-aware supervisions and beyond under the guidance of a teacher network.  ... 
arXiv:2106.10823v2 fatcat:z2lytpximjeyzmnrtlltklvk5a

3D Object Detection from Images for Autonomous Driving: A Survey [article]

Xinzhu Ma, Wanli Ouyang, Andrea Simonelli, Elisa Ricci
2022 arXiv   pre-print
Benefiting from the rapid development of deep learning technologies, image-based 3D detection has achieved remarkable progress.  ...  In retrospect of what has been achieved so far, we also analyze the current challenges in the field and discuss future directions for image-based 3D detection research.  ...  LIGA Stereo (Guo et al.) GUP Net (Lu et al.)  ... 
arXiv:2202.02980v2 fatcat:2hela3uz2bgmtgyzpw5sqslqla

Unifying Voxel-based Representation with Transformer for 3D Object Detection [article]

Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian Sun, Jiaya Jia
2022 arXiv   pre-print
In this way, geometry-aware expressions in point clouds and context-rich features in images are well utilized for better performance and robustness.  ...  The proposed method aims to unify multi-modality representations in the voxel space for accurate and robust single- or cross-modality 3D detection.  ...  A prior work is LIGA-Stereo [37] that transfers geometry-aware representations from LiDAR to stereo images via distillation.  ... 
arXiv:2206.00630v1 fatcat:uz6ej6qxzvaaxieqg2jkyjyfae