Article
Materials Science, Multidisciplinary
Nan Zhou, Yue Sun, Q. Hou, T. Sakakibara, X. Z. Xing, C. Q. Xu, C. Y. Xi, Z. S. Wang, Y. F. Zhang, Y. Q. Pan, B. Chen, X. Luo, Y. P. Sun, Xiaofeng Xu, T. Tamegai, Mingxiang Xu, Zhixiang Shi
Summary: In this study, torque magnetometry was used to investigate the angle-resolved in-plane and out-of-plane magnetic torque for high-quality FeSe1,Sx single crystals. A fourfold torque signal was observed when the magnetic field was within the ab plane, which was interpreted as intrinsic pinning due to the combined effects of gap nodes/minimum and twin domains. Additionally, the observed out-of-plane torque peaks were attributed to intrinsic pinning caused by the layered structure.
MATERIALS TODAY PHYSICS
(2023)
Article
Computer Science, Software Engineering
Yi-Ling Qiao, Lin Gao, Shu-Zhi Liu, Ligang Liu, Yu-Kun Lai, Xilin Chen
Summary: In this article, a learning-based approach is proposed to detect intrinsic reflectional symmetry, which overcomes the issues of high computational cost and randomness. By parametrizing self-isometry using a functional map matrix, the method achieves robustness and generalization to new shapes and withstands perturbation of eigenfunctions. The learning-based algorithm is over 20 times faster than state-of-the-art methods and achieves higher correspondence accuracy.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Remote Sensing
ShaoCong Liu, Tao Wang, Yan Zhang, Ruqin Zhou, Chenguang Dai, Yongsheng Zhang, Haozhen Lei, Hanyun Wang
Summary: This study focuses on the detection of 3D keypoints for large-scale point clouds using deep learning. Four different detection methods based on the D3Feat framework are discussed and evaluated on indoor and outdoor point cloud datasets. The results show that the Multi-layer Perceptron (MLP) based method achieves the best inlier ratios and performs state-of-the-art registration in large-scale point cloud applications.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Environmental Sciences
Sheng Xu, Xin Li, Jiayan Yun, Shanshan Xu
Summary: This paper proposes a four-step framework for tree skeleton extraction, achieving complete skeletons through optimizing paths and interpolating points, and providing an efficient solution for tree skeleton and structure study.
Article
Computer Science, Artificial Intelligence
Rui Qian, Xin Lai, Xirong Li
Summary: Autonomous driving is considered a promising solution to protecting humans from serious accidents. 3D object detection plays a crucial role in the perception system, specifically in path planning, motion prediction, and collision avoidance. However, the field of 3D object detection for autonomous driving is still in its early stages, facing challenges such as visual appearance recovery without depth information, representation learning from partially occluded point clouds, and semantic alignments across different modalities. This comprehensive survey aims to address this gap by examining sensors, datasets, performance metrics, and recent state-of-the-art detection methods, along with their advantages and disadvantages. The article also provides quantitative comparisons and case studies, including runtime analysis, error analysis, and robustness analysis.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Wenfeng Pang, Qianhua He, Yanxiong Li
Summary: This paper proposes a novel Skeleton-Transformer (SkT) method for video anomaly detection. The SkT predicts future pose components in video frames and calculates the errors between predicted and expected values as anomaly scores. The experimental results show that the proposed method achieves good performance on the HR-ShanghaiTech dataset, surpassing existing methods.
MULTIMEDIA SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Ziyu Zhang, Feipeng Da
Summary: This paper proposes a method to improve the robustness and generalization of 3D models on partial point clouds by self-supervised latent feature learning. By explicitly learning the perspective and occlusion transformations in the latent feature space, the proposed method consistently improves the robustness of state-of-the-art methods on point clouds completion datasets.
PATTERN RECOGNITION LETTERS
(2023)
Review
Geography, Physical
Uwe Stilla, Yusheng Xu
Summary: This article provides a comprehensive review of point-cloud-based 3D change detection for urban objects. The study aims to identify critical techniques and explore the applications of point clouds in various fields such as land cover monitoring and transportation monitoring. The limitations of current change detection technology and research gaps are also discussed.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Software Engineering
Anling Jiang, Ji Liu, Jianling Zhou, Min Zhang
Summary: This paper presents a method for extracting the skeleton of 3D tree-shaped point clouds using graph contraction and topology-preserving techniques, which has been validated on various types of point clouds.
Article
Construction & Building Technology
Cedrique Fotsing, Nareph Menadjou, Christophe Bobda
Summary: The study introduces a novel plane detection method based on region growing and the ICP algorithm, which improves the classification of candidate planes by using voxel grids and the number of voxel cells, resulting in better accuracy and efficiency compared to traditional methods.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Chemistry, Multidisciplinary
Dena Bazazian, M. Eulalia Pares
Summary: This paper introduces a novel technique for edge detection in 3D point clouds based on a capsule network architecture, identifying edge features in large scale point clouds and enhancing performance through weakly-supervised learning; Experimental results demonstrate the robust and efficient performance of the proposed EDC-Net on the ABC and ShapeNet datasets.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Hui Chen, Fangyong Xu
Summary: Three dimensional symmetry plane detection is a hot research topic in computer vision. This study proposes a method based on 2D image and transformation to detect the symmetry plane in a 3D point cloud. Experimental results show that the proposed method is effective for both complete and incomplete point clouds, and the detected symmetry plane is more accurate compared to other methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
David Podgorelec, Luka Lukac, Borut Zalik
Summary: This paper presents a new algorithm for detecting reflection symmetry in Earth observation data. The algorithm addresses the challenges of approximate symmetry detection in this specific dataset by voxelization. It first extracts interesting voxels and then finds symmetric pairs of line segments for each horizontal voxel slice. The results are merged to detect maximal symmetric patterns, which can be further processed to identify global and local symmetries.
Article
Construction & Building Technology
Shengjun Tang, Hongsheng Huang, Yunjie Zhang, Mengmeng Yao, Xiaoming Li, Linfu Xie, Weixi Wang
Summary: This study presents a method to generate synthetic noisy point clouds from BIM models and assesses their potential to improve deep neural network training. Experimental results demonstrate a significant improvement in 3D semantic segmentation accuracy by leveraging synthetic point clouds.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Computer Science, Artificial Intelligence
Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi
Summary: In this paper, a self-training method called ST3D++ is proposed for unsupervised domain adaptation on 3D object detection. It aims to reduce noise in pseudo label generation and alleviate the negative impacts of noisy pseudo labels on model training. The method achieves state-of-the-art performance on four benchmark datasets and outperforms the corresponding baseline by a large margin. It even surpasses the fully supervised oracle results on the KITTI 3D object detection benchmark.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Software Engineering
Yuan Gan, Yan Zhang, Zhengxing Sun, Hao Zhang
COMPUTERS & GRAPHICS-UK
(2020)
Article
Computer Science, Software Engineering
Ruizhen Hu, Zeyu Huang, Yuhan Tang, Oliver van Kaick, Hao Zhang, Hui Huang
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Hao Xu, Ka-Hei Hui, Chi-Wing Fu, Hao Zhang
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Ali Mahdavi-Amiri, Fenggen Yu, Haisen Zhao, Adriana Schulz, Hao Zhang
ACM TRANSACTIONS ON GRAPHICS
(2020)
Article
Computer Science, Software Engineering
Ruizhen Hu, Juzhan Xu, Bin Chen, Minglun Gong, Hao Zhang, Hui Huang
ACM TRANSACTIONS ON GRAPHICS
(2020)
Editorial Material
Computer Science, Software Engineering
Torsten Moeller, Richard Zhang
Summary: This article mainly includes the announcement of the Best Paper and Best Associate Editor awards, expressing gratitude to the outgoing Editorial Board members and introducing their replacements. It also outlines the articles published in this New Year's issue.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2022)
Editorial Material
Computer Science, Software Engineering
Richard Zhang
Summary: This article announces the winners of the new IEEE CG&A Test of Time Award and outlines the selection process.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Yanran Guan, Han Liu, Kun Liu, Kangxue Yin, Ruizhen Hu, Oliver van Kaick, Yan Zhang, Ersin Yumer, Nathan Carr, Radomir Mech, Hao Zhang
Summary: This paper introduces a modeling tool that can evolve a set of 3D objects in a functionality-aware manner. By recombining parts, the shapes are evolved to generate large and diverse sets of plausible objects. This tool is significant for data augmentation, constrained modeling, and open-ended exploration, as it can complement existing datasets and improve the performance of contemporary data-driven segmentation schemes.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Editorial Material
Computer Science, Software Engineering
Richard Zhang
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2022)
Editorial Material
Computer Science, Software Engineering
Richard Zhang
Summary: This article presents the recipients of CS Best Paper Awards for 2021.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Manyi Li, Hao Zhang
Summary: The network is the first of its kind to focus on recovering 3D geometric details from a single-view input image. It utilizes two decoders to reconstruct coarse shape and surface details, with three losses ensuring accurate reconstruction through a novel Laplacian term.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Or Patashnik, Dov Danon, Hao Zhang, Daniel Cohen-Or
Summary: BalaGAN is a new unsupervised translation network designed specifically to tackle domain imbalance issues. By leveraging the latent modes of the richer domain, it transforms the image translation problem into a multi-class translation problem, improving the quality of translated images.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Engineering, Electrical & Electronic
Kangxue Yin, Zhiqin Chen, Siddhartha Chaudhuri, Matthew Fisher, Vladimir G. Kim, Hao Zhang
2020 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2020)
(2020)
Article
Computer Science, Artificial Intelligence
Zili Yi, Zhiqin Chen, Hao Cai, Wendong Mao, Minglun Gong, Hao Zhang
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Software Engineering
Pengfei Xu, Jianqiang Ding, Hao Zhang, Hui Huang
COMPUTATIONAL VISUAL MEDIA
(2019)