We present a compression scheme for multiview imagery that facilitates high scalability and accessibility of the compressed content. Our scheme relies upon constructing at a single base view, a disparity model for a group of views, and then utilizing this base-anchored model to infer disparity at all views belonging to the group. We employ a hierarchical disparity-compensated inter-view transform where the corresponding analysis and synthesis filters are applied along the geometric flows defined by the base-anchored disparity model. The output of this inter-view transform along with the disparity information is subjected to spatial wavelet transforms and embedded block-based coding. Rate-distortion results reveal superior performance to the x.265 anchor chosen by the JPEG Pleno standards activity for the coding of multiview imagery captured by high-density camera arrays.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2019.2894968 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Motor Imagery EEG Classification Based on Multi-Domain Feature Rotation and Stacking Ensemble.
Brain Sci
January 2025
School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.
Background: Decoding motor intentions from electroencephalogram (EEG) signals is a critical component of motor imagery-based brain-computer interface (MI-BCIs). In traditional EEG signal classification, effectively utilizing the valuable information contained within the electroencephalogram is crucial.
Objectives: To further optimize the use of information from various domains, we propose a novel framework based on multi-domain feature rotation transformation and stacking ensemble for classifying MI tasks.
A multi-branch, multi-scale, and multi-view CNN with lightweight temporal attention mechanism for EEG-based motor imagery decoding.
Comput Methods Biomech Biomed Engin
January 2025
The School of Computer Science, Hangzhou Dianzi University, Hangzhou, China.
Convolutional neural networks (CNNs) have been widely utilized for decoding motor imagery (MI) from electroencephalogram (EEG) signals. However, extracting discriminative spatial-temporal-spectral features from low signal-to-noise ratio EEG signals remains challenging. This paper proposes MBMSNet , a multi-branch, multi-scale, and multi-view CNN with a lightweight temporal attention mechanism for EEG-Based MI decoding.
View Article and Find Full Text PDFFaSS-MVS: Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-Borne Monocular Imagery.
Sensors (Basel)
October 2024
Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany.
Article Synopsis
- * The technique uses a hierarchical approach, employing a plane-sweep algorithm combined with semi-global optimization to accurately create 3D models from large scenes typically seen in low-altitude drone images.
- * In tests, FaSS-MVS produces 3D data with high accuracy comparable to advanced offline methods like COLMAP, but does so much faster, processing images at 1-2 frames per second with significantly less computational time.
Efficient Multi-View Graph Convolutional Network with Self-Attention for Multi-Class Motor Imagery Decoding.
Bioengineering (Basel)
September 2024
College of Computer Science, Beijing University of Technology, Beijing 100124, China.
Article Synopsis
- Research in motor imagery using EEG signals is crucial for brain-computer interfaces (BCI), but current deep-learning methods struggle to leverage the complex relationships between brain regions.
- The study introduces a new model called MGCANet, which incorporates multi-view graph convolution and attention mechanisms to better aggregate and analyze EEG data from different brain areas for improved classification accuracy.
- Experimental results show that MGCANet achieved impressive accuracies of 78.26% and 73.68% on two public datasets, outperforming existing classification methods and offering fresh insights into motor imagery decoding.
Graph-DETR4D: Spatio-Temporal Graph Modeling for Multi-View 3D Object Detection.
IEEE Trans Image Process
August 2024
Multi-View 3D object detection (MV3D) has made tremendous progress by leveraging multiple perspective features through surrounding cameras. Despite demonstrating promising prospects in various applications, accurately detecting objects through camera view in the 3D space is extremely difficult due to the ill-posed issue in monocular depth estimation. Recently, Graph-DETR3D presents a novel graph-based 3D-2D query paradigm in aggregating multi-view images for 3D object detection and achieves competitive performance.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!