相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Geochemistry & Geophysics
Ming Cheng et al.
Summary: This article introduces a novel dense point cloud completion architecture based on generative adversarial networks, utilizing two generator and discriminator modules to achieve complete reconstruction of incomplete point clouds. Experimental results demonstrate that DPCG-Net outperforms other models in cases with a large proportion of missing point clouds, showing effectiveness in both synthetic and real-world scenarios.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Review
Engineering, Civil
Ben Fei et al.
Summary: This paper provides a comprehensive survey on various methods for point cloud completion, summarizes the comparisons among these methods, and discusses possible research trends in this rapidly expanding field.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
Summary: This paper presents a self-supervised learning method for computer vision based on masked autoencoders. By masking a portion of the input image and reconstructing the missing pixels, large models can be trained efficiently and effectively. The approach achieves high generalization performance and outperforms supervised pretraining in transfer learning tasks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Software Engineering
Yongwei Miao et al.
Summary: The study introduces an end-to-end shape-preserving point completion network that works directly on incomplete 3D point clouds, restoring their overall shapes and fine-scale structures. Experimental results show that the network performs well in completing tasks and outperforms state-of-the-art methods in terms of Chamfer distance and earth mover's distance errors.
IEEE COMPUTER GRAPHICS AND APPLICATIONS
(2021)
Article
Robotics
Jieqi Shi et al.
Summary: This study introduces a graph-guided deformation network for point cloud completion, which simulates traditional graphic algorithms and reduces the gap between completion tasks and mesh deformation algorithms. Experimental results show that this method outperforms existing state-of-the-art algorithms on various datasets.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Chemistry, Medicinal
Carmen Esposito et al.
Summary: The study presents two automated procedures for selecting the optimal decision threshold for imbalanced classification, which do not require retraining of models. Testing on drug discovery datasets shows that these thresholding methods significantly improve the performance of RF.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaogang Wang et al.
Summary: The paper introduces VE-PCN, a voxel-based network for point cloud completion using edge generation. By embedding point clouds into voxel grids and generating complete objects with hallucinated shape edges, the model is able to produce more realistic surface details. It outperforms existing state-of-the-art approaches quantitatively and qualitatively on completion datasets.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xin Wen et al.
Summary: This paper introduces a new perspective on point cloud completion task by formulating the prediction as a point cloud deformation process using a novel neural network named PMP-Net. PMP-Net predicts unique point moving paths for each point to improve the quality of the predicted complete shape through shortest total point moving distances. Experimental results on Completion3D and PCN datasets show advantages over state-of-the-art point cloud completion methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Chulin Xie et al.
Summary: A novel Style-based Point Generator with Adversarial Rendering (SpareNet) is proposed for point cloud completion. The method utilizes channel-attentive EdgeConv, style code modulation during folding, and projection of completed points to depth maps, achieving state-of-the-art quantitative performance and superior visual quality.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Junzhe Zhang et al.
Summary: ShapeInversion is an unsupervised 3D shape completion method based on Generative Adversarial Network (GAN) inversion, which reconstructs complete shapes for partial inputs by searching for latent codes. It outperforms state-of-the-art unsupervised methods on the ShapeNet benchmark and demonstrates remarkable generalization ability for real-world scans and various forms of partial inputs. Additionally, ShapeInversion enables additional capabilities such as producing multiple valid complete shapes for ambiguous partial inputs and shape manipulation.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Cheng Wen et al.
Summary: This paper proposes a dual-generators framework for point cloud generation, which progressively learns effective point embeddings for accurate point cloud generation. Experimental results demonstrate the state-of-the-art performance of the proposed method for accurate point cloud generation on a variety of object categories from the ShapeNet dataset.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xin Wen et al.
Summary: In this paper, a novel unpaired point cloud completion network named Cycle4Completion is proposed to infer complete geometries from partial 3D objects through bidirectional geometry correspondence learning. Experimental results demonstrate that the model outperforms state-of-the-art unpaired completion methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Robotics
Liang Pan
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Computer Science, Software Engineering
Isaak Lim et al.
COMPUTER GRAPHICS FORUM
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Lyne P. Tchapmi et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
