Guo-Qiang Xiao

Hui-Xian Cheng, Xian-Feng Han, Guo-Qiang Xiao

Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{concise} and \textbf{efficient} image-based semantic segmentation network, named \textbf{CENet}. In order to improve the descriptive power of learned features and reduce the computational as well as time complexity, our CENet integrates the convolution with larger kernel size instead of MLP, carefully-selected activation functions, and multiple auxiliary segmentation heads with corresponding loss functions into architecture. Quantitative and qualitative experiments conducted on publicly available benchmarks, SemanticKITTI and SemanticPOSS, demonstrate that our pipeline achieves much better mIoU and inference performance compared with state-of-the-art models. The code will be available at https://github.com/huixiancheng/CENet.

Xian-Feng Han, Zhang-Yue He, Jia Chen et al.

Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. And its permutation invariance property makes it ideally suitable for point cloud processing. Inspired by this remarkable success, we propose an end-to-end architecture, dubbed Cross-Level Cross-Scale Cross-Attention Network (CLCSCANet), for point cloud representation learning. First, a point-wise feature pyramid module is introduced to hierarchically extract features from different scales or resolutions. Then a cross-level cross-attention is designed to model long-range inter-level and intra-level dependencies. Finally, we develop a cross-scale cross-attention module to capture interactions between-and-within scales for representation enhancement. Compared with state-of-the-art approaches, our network can obtain competitive performance on challenging 3D object classification, point cloud segmentation tasks via comprehensive experimental evaluation.

Xian-Feng Han, Yi-Fei Jin, Hui-Xian Cheng et al.

Following the tremendous success of transformer in natural language processing and image understanding tasks, in this paper, we present a novel point cloud representation learning architecture, named Dual Transformer Network (DTNet), which mainly consists of Dual Point Cloud Transformer (DPCT) module. Specifically, by aggregating the well-designed point-wise and channel-wise multi-head self-attention models simultaneously, DPCT module can capture much richer contextual dependencies semantically from the perspective of position and channel. With the DPCT module as a fundamental component, we construct the DTNet for performing point cloud analysis in an end-to-end manner. Extensive quantitative and qualitative experiments on publicly available benchmarks demonstrate the effectiveness of our proposed transformer framework for the tasks of 3D point cloud classification and segmentation, achieving highly competitive performance in comparison with the state-of-the-art approaches.

Xian-Feng Han, Shi-Jie Sun, Xiang-Yu Song et al.

The introduction of inexpensive 3D data acquisition devices has promisingly facilitated the wide availability and popularity of 3D point cloud, which attracts more attention to the effective extraction of novel 3D point cloud descriptors for accuracy of the efficiency of 3D computer vision tasks in recent years. However, how to develop discriminative and robust feature descriptors from 3D point cloud remains a challenging task due to their intrinsic characteristics. In this paper, we give a comprehensively insightful investigation of the existing 3D point cloud descriptors. These methods can principally be divided into two categories according to the advancement of descriptors: hand-crafted based and deep learning-based apporaches, which will be further discussed from the perspective of elaborate classification, their advantages, and limitations. Finally, we present the future research direction of the extraction of 3D point cloud descriptors.