arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08116cs.CV
收藏

PerMO:从一张图像中一次感知更多内容,实现自动驾驶

PerMO: Perceiving More at Once from a Single Image for Autonomous Driving

Feixiang Lu, Zongdai Liu, Xibin Song, Dingfu Zhou, Wei Li, Hui Miao, Miao Liao, Liangjun Zhang, Bin Zhou, Ruigang Yang, Dinesh Manocha

摘要:

我们提出了一种新的方法来检测,分割和重建完整的纹理3D模型的车辆从一个单一的图像自动驾驶。我们的方法结合了深度学习的优势和传统技术的优雅,从基于零件的可变形模型表示,以在存在严重遮挡的情况下生成高质量的3D模型。我们提出了一种新的基于零件的可变形车辆模型,用于实例分割,并自动生成一个数据集,包含密集的二维图像和三维模型之间的对应关系。我们还提出了一种新型的端到端深度神经网络来预测密集的2D/3D映射并突出其优点。基于密集映射,我们能够在商品GPU上以几乎交互的速率计算精确的6-DoF姿势和3D重建结果。我们已经将这些算法与自动驾驶系统集成在一起。在实践中,我们的方法优于所有主要车辆解析任务的最先进的方法:2D实例分割4.4点(mAP),6自由度姿态估计9.11点,3D检测1.37。此外,我们已经在Github上发布了所有的源代码,数据集和训练模型。

英文摘要:

We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image for autonomous driving. Our approach combines the strengths of deep learning and the elegance of traditional techniques from part-based deformable model representation to produce high-quality 3D models in the presence of severe occlusions. We present a new part-based deformable vehicle model that is used for instance segmentation and automatically generate a dataset that contains dense correspondences between 2D images and 3D models. We also present a novel end-to-end deep neural network to predict dense 2D/3D mapping and highlight its benefits. Based on the dense mapping, we are able to compute precise 6-DoF poses and 3D reconstruction results at almost interactive rates on a commodity GPU. We have integrated these algorithms with an autonomous driving system. In practice, our method outperforms the state-of-the-art methods for all major vehicle parsing tasks: 2D instance segmentation by 4.4 points (mAP), 6-DoF pose estimation by 9.11 points, and 3D detection by 1.37. Moreover, we have released all of the source code, dataset, and the trained model on Github.

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。

↑