We present RangeRCNN, a novel and effective 3D object detection framework based on the range image representation. Most existing 3D object detection methods are either voxel-based or point-based. Though several optimizations have been introduced to ease the sparsity issue and speed up the running time, the two representations are still computationally inefficient. Compared to these two representations, the range image representation is dense and compact which can exploit the powerful 2D convolution and avoid the uncertain receptive field caused by the sparsity issue. Even so, the range image representation is not preferred in 3D object detection due to the scale variation and occlusion. In this paper, we utilize the dilated residual block to better adapt different object scales and obtain a more flexible receptive field on range image. Considering the scale variation and occlusion of the range image, we propose the RV-PV-BEV (Range View to Point View to Bird's Eye View) module to transfer the feature from the range view to the bird's eye view. The anchor is defined in the BEV space which avoids the scale variation and occlusion. Both RV and BEV cannot provide enough information for height estimation, so we propose a two-stage RCNN for better 3D detection performance. The point view aforementioned does not only serve as a bridge from RV to BEV but also provides pointwise features for RCNN. Extensive experiments show that the proposed RangeRCNN achieves state-of-the-art performance on the KITTI 3D object detection dataset. We prove that the range image based methods can be effective on the KITTI dataset which provides more possibilities for real-time 3D object detection.
This paper addresses the problem of the semantic segmentation of large-scale 3D road scenes by incorporating the complementary advantages of point clouds and images. To make full use of geometrical and visual information, this paper extracts 3D geometric features from a point cloud using a deep neural network for 3D semantic segmentation and extracts 2D visual features from images using a Convolutional Neural Network (CNN) for 2D semantic segmentation. In order to bridge the features of the two modalities, this paper uses superpoints as an intermediate representation to connect the 2D features with the 3D features. A superpoint-based pooling method is proposed to fuse the features from the two different modalities for joint learning. To evaluate the approach, the paper generates 3D scenes from the Virtual KITTI dataset. The results of the experiments demonstrate that the proposed approach is capable of segmenting large-scale 3D road scenes based on the compact and semantically homogeneous superpoints, and that it achieves considerable improvements over the 2D image and 3D point cloud semantic segmentation methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.