☆ 4.7 Article

Task-Oriented Compact Representation of 3D Point Clouds via A Matrix Optimization-Driven Network

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

A Hybrid Compression Framework for Color Attributes of Static 3D Point Clouds

Hao Liu et al.

Summary: This study proposes a novel and efficient color attribute compression method for static 3D point clouds, which involves partitioning the point cloud based on color distribution analysis, decomposing them into 3D blocks using an improved k-d tree algorithm, and utilizing a sparse representation strategy with virtual adaptive sampling. Experimental results show that this method achieves superior coding performance compared to current state-of-the-art methods.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep Coarse-to-Fine Dense Light Field Reconstruction With Flexible Sampling and Geometry-Aware Fusion

Jing Jin et al.

Summary: In this paper, a novel learning-based method is proposed to reconstruct densely-sampled light fields with arbitrary angular resolution from sparsely-sampled light fields with irregular structures. The proposed method, which is an end-to-end trainable network, achieves high reconstruction quality and computational efficiency by synthesizing coarse sub-aperture images and refining the angular relationship. Experimental results demonstrate the superiority of the proposed method in various light field applications, including image-based rendering and depth estimation enhancement.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

APSNet: Toward Adaptive Point Sampling for Efficient 3D Action Recognition

Jiaheng Liu et al.

Summary: This paper investigates the trade-off between accuracy and efficiency in 3D action recognition. A simple and efficient backbone network structure and an adaptive point sampling network are proposed to achieve this trade-off. Experimental results demonstrate the effectiveness and efficiency of the proposed approach for 3D action recognition.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

Add to Collection

Article Computer Science, Information Systems

Convolutional Neural Network-Based Occupancy Map Accuracy Improvement for Video-Based Point Cloud Compression

Wei Jia et al.

Summary: In video-based point cloud compression, we propose using a convolutional neural network (CNN) to improve the accuracy of the occupancy map video, resulting in more accurate occupancy map videos and significant bitrate savings.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Lossy Point Cloud Geometry Compression via Region-Wise Processing

Wenjie Zhu et al.

Summary: The region-wise approach for point cloud geometry compression divides the point cloud surface into local regions and describes the geometry shape numerically using surface vectors for efficient compression. Grouping regions into discriminative clusters minimizes inter-cluster similarity and maximizes intra-cluster similarity, with encoding reference regions directly and signaling non-reference regions through associated transform parameters. This method offers remarkable coding efficiency improvement compared to octree-based approaches, with significant gains in distortion evaluations.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Lossy Point Cloud Geometry Compression via End-to-End Learning

Jianqiang Wang et al.

Summary: This paper introduces a novel system for compressing point cloud geometry using deep neural networks and variational autoencoders, which outperforms existing standardized methods in both objective performance and subjective visual quality. The method has a small parameter size and is suitable for practical implementation, even on embedded platforms.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

View-Dependent Dynamic Point Cloud Compression

Wenjie Zhu et al.

Summary: The proposed view-dependent DPC compression technique, View-PCC, utilizes both global and local projection to efficiently map 3D points, and encodes the images using boundary padding and the HEVC standard for better compression results. The approach shows significant objective compression gains compared to traditional methods and offers better reconstruction quality in subjective quality assessment compared to V-PCC.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-Scale Neighborhood Feature Extraction and Aggregation for Point Cloud Segmentation

Dawei Li et al.

Summary: The paper introduces a Multi-scale Neighborhood Feature Extraction and Aggregation Model (MNFEAM) to enhance feature extraction for point cloud learning, and designs a new discriminative loss function to improve the performance of point cloud segmentation networks.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Multi-Scale Structured Dictionary Learning for 3-D Point Cloud Attribute Compression

Yangmei Shen et al.

Summary: The article proposes a multi-scale structured dictionary learning algorithm for 3-D point cloud attribute compression, which leverages hierarchical sparsity within signals and supports encoding voxelized point cloud attributes with progressive refinement of high-frequency details.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PC-Net: A Deep Network for 3D Point Clouds Analysis

Zhuo Chen et al.

Summary: This work proposes a simple yet effective approach for 3D Point Clouds analysis, named PC-Net, which learns directly on point sets with novel operations and hierarchical neural network design, demonstrating state-of-the-art performance on popular benchmarks for classification and segmentation tasks.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Add to Collection

Article Computer Science, Information Systems

Patch Based Video Summarization With Block Sparse Representation

Shaohui Mei et al.

Summary: This paper proposes a video summarization method based on block sparse representation, involving partitioning video frames into patches and characterizing each patch with global features, considering reconstruction constraints, and solving the model using the SBOMP algorithm. The model is further extended to a neighborhood based model, one of the first to consider both spatial and temporal contexts in sparse representation based video summarization methods.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Pointwise geometric and semantic learning network on 3D point clouds

Dejun Zhang et al.

INTEGRATED COMPUTER-AIDED ENGINEERING (2020)

Add to Collection

Article Engineering, Electrical & Electronic

A Comprehensive Study and Comparison of Core Technologies for MPEG 3-D Point Cloud Compression

Hao Liu et al.

IEEE TRANSACTIONS ON BROADCASTING (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Emerging MPEG Standards for Point Cloud Compression

Sebastian Schwarz et al.

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS (2019)

Add to Collection

Article Computer Science, Software Engineering

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning

Yujin Chen et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PU-GAN: a Point Cloud Upsampling Adversarial Network

Ruihui Li et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Deep Closest Point: Learning Representations for Point Cloud Registration

Yue Wang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PointNetLK: Robust & Efficient Point Cloud Registration using PointNet

Yasuhiro Aoki et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Patch-based Progressive 3D Point Set Upsampling

Wang Yifan et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling

Jiancheng Yang et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Information Systems

DEEP LEARNING-BASED POINT CLOUD CODING: A BEHAVIOR AND PERFORMANCE STUDY

Andre F. R. Guarda et al.

2019 8TH EUROPEAN WORKSHOP ON VISUAL INFORMATION PROCESSING (EUVIP 2019) (2019)

Add to Collection

Proceedings Paper Imaging Science & Photographic Technology

LEARNING CONVOLUTIONAL TRANSFORMS FOR LOSSY POINT CLOUD GEOMETRY COMPRESSION

Maurice Quach et al.

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2019)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

3D Point Cloud Geometry Compression on Deep Learning

Tianxin Huang et al.

PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19) (2019)

Add to Collection

Article Engineering, Electrical & Electronic

A Coarse-to-Fine Algorithm for Matching and Registration in 3D Cross-Source Point Clouds

Xiaoshui Huang et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition

Mikaela Angelina Uy et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Article Robotics

Integrating Deep Semantic Segmentation Into 3-D Point Cloud Registration

Anestis Zaganidis et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

3D Point Cloud Registration for Localization using a Deep Neural Network Auto-Encoder

Gil Elbaz et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking

Qi Wang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2016)

Add to Collection

Article Computer Science, Artificial Intelligence

Geometric 3D point cloud compression

Vicente Morell et al.

PATTERN RECOGNITION LETTERS (2014)

Add to Collection

Article Computer Science, Software Engineering

An Intrinsic Algorithm for Parallel Poisson Disk Sampling on Arbitrary Surfaces

Xiang Ying et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2013)

Add to Collection

Article Geochemistry & Geophysics

Band, selection for hyperspectral image classification using mutual information

Baofeng Guo et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.