Image Quality, Uniformity and Computation Improvement of Compressive Light Field Displays with U-Net
arXiv:2312.16987v1h-index: 21SID Symp Dig Tech Pap
Originality Synthesis-oriented
AI Analysis
This work addresses display technology for applications like VR/AR, but it is incremental as it adapts an existing model to a specific domain.
The paper tackles the problem of compressive light field synthesis by applying the U-Net model, resulting in improved image quality, uniformity, and reduced computation compared to existing methods.
We apply the U-Net model for compressive light field synthesis. Compared to methods based on stacked CNN and iterative algorithms, this method offers better image quality, uniformity and less computation.