AI Article Synopsis
- This study introduces a new method for compressing dense light field images captured by Plenoptic 2.0 cameras, using advanced statistical models like the 5-D Epanechnikov Kernel.
- To address limitations in traditional modeling techniques, the researchers propose a novel 5-D Epanechnikov Mixture-of-Experts approach that uses Gaussian Initialization, which performs better than existing models like 5-D Gaussian Mixture Regression.
- Experimental results show that this new compression method produces higher quality rendered images than High Efficiency Video Coding (HEVC) and JPEG 2000, especially at low bit depths below 0.06 bits per pixel (bpp).
Article Abstract
In this study, we propose a modeling-based compression approach for dense/lenslet light field images captured by Plenoptic 2.0 with square microlenses. This method employs the 5-D Epanechnikov Kernel (5-D EK) and its associated theories. Owing to the limitations of modeling larger image block using the Epanechnikov Mixture Regression (EMR), a 5-D Epanechnikov Mixture-of-Experts using Gaussian Initialization (5-D EMoE-GI) is proposed. This approach outperforms 5-D Gaussian Mixture Regression (5-D GMR). The modeling aspect of our coding framework utilizes the entire EI and the 5D Adaptive Model Selection (5-D AMLS) algorithm. The experimental results demonstrate that the decoded rendered images produced by our method are perceptually superior, outperforming High Efficiency Video Coding (HEVC) and JPEG 2000 at a bit depth below 0.06bpp.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2024.3418350 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
5-D Epanechnikov Mixture-of-Experts in Light Field Image Compression.
IEEE Trans Image Process
July 2024
Article Synopsis
- This study introduces a new method for compressing dense light field images captured by Plenoptic 2.0 cameras, using advanced statistical models like the 5-D Epanechnikov Kernel.
- To address limitations in traditional modeling techniques, the researchers propose a novel 5-D Epanechnikov Mixture-of-Experts approach that uses Gaussian Initialization, which performs better than existing models like 5-D Gaussian Mixture Regression.
- Experimental results show that this new compression method produces higher quality rendered images than High Efficiency Video Coding (HEVC) and JPEG 2000, especially at low bit depths below 0.06 bits per pixel (bpp).
Want 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!