Summary of Configurable Learned Holography, by Yicheng Zhan et al.
Configurable Learned Holography
by Yicheng Zhan, Liang Shi, Wojciech Matusik, Qi Sun, Kaan Akşit
First submitted to arxiv on: 24 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Graphics (cs.GR); Machine Learning (cs.LG); Image and Video Processing (eess.IV); Optics (physics.optics)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a configurable learned model that can generate 3D holograms from RGB-only 2D images for various holographic displays without requiring retraining. The model is conditioned to predefined hardware parameters, such as working wavelengths and pixel pitch, allowing it to adapt to different display configurations. The approach accommodates multiple hologram types, including single-color and multi-color holograms. The paper also introduces a novel correlation-based learning strategy that identifies the relationship between depth estimation and 3D hologram synthesis tasks. The model achieves up to a 2x speed improvement compared to state-of-the-art models while maintaining high-quality hologram generation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps make holographic displays better by creating a smart model that can generate 3D holograms from regular 2D pictures for different display settings without needing to be retrained. This means the model can quickly adjust to changes in display hardware, making it useful for many applications. The approach also allows for different types of holograms and is faster than previous models. |
Keywords
» Artificial intelligence » Depth estimation
