返回
Semantic-aware self-supervised depth estimation for stereo 3D detection
DOI:10.1016/j.patrec.2023.02.006.png)
摘要
En 中文
Besides the 3D object supervision, the auxiliary disparity supervision is usually indispensable when train-ing a stereo-based 3D object detector. The disparity supervision is either transformed from LiDAR points or generated from pre-trained models. However, the former suffers from the high cost and over-sensitivity to airborne particles of LiDAR devices, and the latter from the limited cross-dataset transferability of con-temporary stereo matching models. To alleviate those problems, we propose a self-supervision frame-work for stereo-based 3D detection that relies on neither LiDARs nor external models. A Depth-based Self-supervision (DSelf) is proposed to unify the coordinate spaces of self-supervised losses and detection into a 3D space. However, the DSelf supervision is dense compared with the sparse LiDAR points, which introduces redundancy and irrelevancy into the stereo features. A Semantic-Aware Sampler (SASampler) is proposed to address the problems by an unbalanced sampling of foreground and background pixels. Combining our SASampler and DSelf supervision, the resultant detector (named S3D) achieves state-of-the-art detection results without explicit disparity supervisions. (c) 2023 Published by Elsevier B.V.
Keyword:
Stereo vision
3D object detection
Self-supervised learning
Depth estimation
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
GRNet: Graph-based remodeling network for multi-view semi-supervised classificationGRNet: 基于图的多视图半监督分类重构网络
Asynchronous Fault Detection for Interval Type-2 Fuzzy Nonhomogeneous Higher Level Markov Jump Systems With Uncertain Transition Probabilities具有不确定转移概率的区间2型模糊非齐次高阶Markov跳变系统的异步故障检测
没有更多内容

