DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

CVPR(2020)

引用 59|浏览450
暂无评分
摘要
We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes. The core novelty of our method is a fast, single-pass architecture that both detects objects in 3D and estimates their shapes. 3D bounding box parameters are estimated in one pass for every point, aggregated through graph convolutions, and fed into a branch of the network that predicts latent codes representing the shape of each detected object. The latent shape space and shape decoder are learned on a synthetic dataset and then used as supervision for the end-to-end training of the 3D object detection pipeline. Thus our model is able to extract shapes without access to ground-truth shape information in the target dataset. During experiments, we find that our proposed method achieves state-of-the-art results by ~5% on object detection in ScanNet scenes, and it gets top results by 3.4% in the Waymo Open Dataset, while reproducing the shapes of detected cars.
更多
查看译文
关键词
single-pass architecture,3D bounding box parameters,latent shape space,object detection,ground-truth shape information,fast single-stage 3D object detection method,domain-specific design decisions,bird-eye view image,autonomous driving scenarios,indoor scenes,outdoor scenes,fast pass architecture,shape decoder,ScanNet scenes,Waymo Open Dataset,LIDAR data,graph convolutions
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要