arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2203.02112cs.CV
收藏

自动驾驶中用于单目3D目标检测的伪立体方法

Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving

Zhejiang University(浙江大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Yi-Nan Chen, Hang Dai, Yong Ding

摘要:

伪LiDAR 3D探测器通过利用深度估计网络增强感知深度的能力以及使用基于LiDAR的3D探测架构,在单目3D探测方面取得了显著进展。先进的立体3D探测器还可以精确定位3D物体。立体视图的图像到图像生成中的间隙比图像到LiDAR生成中的间隙小得多。基于此,我们提出了一个伪立体3D检测框架与三种新的虚拟视图生成方法,包括图像级生成,特征级生成和特征克隆,用于从单个图像中检测3D对象。我们对深度感知学习的分析表明,在我们的框架中,深度损失仅在特征级虚拟视图生成中有效,估计的深度图在图像级和特征级都有效。我们提出了一种基于视差的动态卷积算法,该算法利用视差特征图中的动态核函数,自适应地从一幅图像中过滤特征,生成虚拟图像特征,从而减轻了由深度估计误差引起的特征退化。截至提交(2021年11月18日),我们的伪立体3D检测框架在KITTI-3D基准测试中发表的单目3D检测器中,在汽车、行人和骑自行车者方面排名第一。代码发布于https://github.com/revisitq/Pseudo-Stereo-3D。

英文摘要:

Pseudo-LiDAR 3D detectors have made remarkable progress in monocular 3D detection by enhancing the capability of perceiving depth with depth estimation networks, and using LiDAR-based 3D detection architectures. The advanced stereo 3D detectors can also accurately localize 3D objects. The gap in image-to-image generation for stereo views is much smaller than that in image-to-LiDAR generation. Motivated by this, we propose a Pseudo-Stereo 3D detection framework with three novel virtual view generation methods, including image-level generation, feature-level generation, and feature-clone, for detecting 3D objects from a single image. Our analysis of depth-aware learning shows that the depth loss is effective in only feature-level virtual view generation and the estimated depth map is effective in both image-level and feature-level in our framework. We propose a disparity-wise dynamic convolution with dynamic kernels sampled from the disparity feature map to filter the features adaptively from a single image for generating virtual image features, which eases the feature degradation caused by the depth estimation errors. Till submission (November 18, 2021), our Pseudo-Stereo 3D detection framework ranks 1st on car, pedestrian, and cyclist among the monocular 3D detectors with publications on the KITTI-3D benchmark. The code is released at https://github.com/revisitq/Pseudo-Stereo-3D.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑