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
Engineering, Electrical & Electronic
Ziwei Wei et al.
Summary: The point cloud is an essential data structure for virtual and mixed reality applications, and efficient point cloud compression technology is crucial for these applications. In this paper, we propose a deep neural network model to predict isolated points in point clouds. Experimental results show that our model achieves significantly higher accuracy compared to the latest prediction methods. Furthermore, our model achieves an average coding gain of 5.29% in lossless geometry point cloud compression, surpassing the state-of-the-art.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Zhiyuan Zhang et al.
Summary: This paper proposes a novel robust 3D point cloud registration framework by learning a new type of virtual points called rectified virtual corresponding points (RCPs), which enables natural registration between source and target point clouds. The method achieves advanced registration performance and time-efficiency simultaneously.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Yunpeng Chang et al.
Summary: This study tackles anomaly detection in videos by exploring a novel convolution autoencoder architecture that separates spatio-temporal representations to capture abnormal events. By simulating differences in appearance and motion behaviors, an effective anomaly detection method is proposed, achieving state-of-the-art performance on multiple public datasets.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Jiayi Ma et al.
Summary: This paper proposes a method called motion-consistency driven matching (MCDM) to remove mismatches between two feature sets. By formulating the matching problem into a probabilistic graphical model and incorporating motion consistency and a general prior, the proposed method can effectively differentiate false correspondences from the true ones. Experimental results demonstrate that MCDM has strong generalization ability and high accuracy, outperforming state-of-the-art methods. Additionally, the proposed method has low computational complexity and is efficient for practical feature matching tasks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zi Jian Yew et al.
Summary: In this paper, a point cloud registration method using attention mechanisms is proposed, which replaces traditional feature matching and RANSAC algorithms by directly predicting the final set of point correspondences. Experimental results show that the proposed method achieves state-of-the-art performance on several benchmarks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Jiayi Ma et al.
Summary: Image matching is a fundamental task in various visual applications, and with the development of deep learning techniques, there has been an increasing number of methods proposed in this field. However, the challenge remains in choosing the suitable method for specific applications and designing image matching methods with superior performance. This comprehensive review and analysis provide insights into classical and latest techniques, and offer prospects for future development in image matching technologies.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Engineering, Electrical & Electronic
Xinju Wu et al.
Summary: This paper focuses on subjective and objective Point Cloud Quality Assessment (PCQA) in immersive environments, studying the impact of geometry and texture attributes in compression distortion. A subjective PCQA database was established using a Head-Mounted Display (HMD), and two projection-based objective quality evaluation methods were proposed. The research findings can be applied in point cloud processing, transmission, and coding for virtual reality applications.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Bingli Wu et al.
Summary: The paper introduces a Feature Interactive Representation learning Network (FIRE-Net) that explores feature interaction between source and target point clouds. By using local and global interaction units, the network improves the registration performance of point clouds.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Hao Xu et al.
Summary: This paper presents a global feature based iterative network OMNet for partial-to-partial point cloud registration, utilizing overlapping masks to reject non-overlapping regions and converting the registration to that of the same shape. By improving the data generation process, the previously prevalent over-fitting issue is avoided.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Taewon Min et al.
Summary: The study proposes a novel positional embedding scheme called the DoPE module, which significantly improves the distinctiveness of high-level features in point cloud registration and enhances point matching and registration accuracy. By using the DoPE module in an iterative registration framework, the two point clouds can be gradually registered to achieve a desired equilibrium after only a few iterations.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Anh-Quan Cao et al.
Summary: PCAM is a neural network that uses a pointwise product of cross-attention matrices to mix low-level geometric and high-level contextual information for finding point correspondences, achieving state-of-the-art results in rigid registration of point clouds with partial overlaps.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuan Liu et al.
Summary: Motion coherence is crucial for distinguishing true correspondences, and the proposed LMCNet combines global and local coherence to robustly detect inlier correspondences, outperforming existing methods in relative camera pose estimation and correspondences pruning in dynamic scenes.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Shengyu Huang et al.
Summary: PREDATOR is a model designed for pairwise point-cloud registration, with a focus on handling low overlap scenarios. Its key innovation lies in the overlap-attention block, which enables early information exchange between the latent encodings of the two point clouds, leading to improved performance in matching relevant points.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Computer Science, Artificial Intelligence
Yujin Chen et al.
Summary: Accurately reconstructing 3D hand and object shapes is crucial for understanding human-object interaction. Unlike traditional bare hand pose estimation, the interaction between hand and object imposes constraints on both, suggesting that considering hand configuration as contextual information for the object is important. Current approaches often use separate branches to reconstruct the hand and object, with little communication between them. This study proposes a joint approach in feature space, exploring the reciprocity between hand and object branches. Through cross-branch feature fusion architectures and an auxiliary depth estimation module, the proposed method outperforms existing approaches in terms of reconstruction accuracy.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuyang Bai et al.
Summary: This paper introduces a novel deep neural network, PointDSC, that explicitly incorporates spatial consistency for pruning outlier correspondences. With modest computation cost, the method outperforms existing handcrafted and learning-based outlier rejection approaches significantly on real-world datasets. It also demonstrates wide applicability when combined with different 3D local descriptors.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Geography, Physical
Jiayuan Li et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
G. Dias Pais et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Xuyang Bai et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Christopher Choy et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Jiayi Ma et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Yujin Chen et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Christopher Choy et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Yue Wang et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Yasuhiro Aoki et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Zan Gojcic et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Huu M. Le et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Automation & Control Systems
Fahira Afzal Maken et al.
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Andy Zeng et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Jiaolong Yang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Qian-Yi Zhou et al.
COMPUTER VISION - ECCV 2016, PT II
(2016)
Article
Computer Science, Artificial Intelligence
Samuele Salti et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2014)
