A Large-Depth-Range Layer-Based Hologram Dataset for Machine Learning-Based 3D Computer-Generated Holography

TL;DR

This paper introduces a large-scale, high-quality hologram dataset called KOREATECH-CGH for machine learning-based 3D holography, along with a novel amplitude projection technique that improves hologram quality across wide depth ranges.

Contribution

The paper provides a new extensive hologram dataset and a post-processing method to enhance hologram quality at large depths, facilitating ML training and evaluation.

Findings

Achieved 27.01 dB PSNR and 0.87 SSIM with the new method.

Dataset covers wide depth ranges up to theoretical limits.

Validated dataset's effectiveness in hologram generation and super-resolution tasks.

Abstract

Machine learning-based computer-generated holography (ML-CGH) has advanced rapidly in recent years, yet progress is constrained by the limited availability of high-quality, large-scale hologram datasets. To address this, we present KOREATECH-CGH, a publicly available dataset comprising 6,000 pairs of RGB-D images and complex holograms across resolutions ranging from 256*256 to 2048*2048, with depth ranges extending to the theoretical limits of the angular spectrum method for wide 3D scene coverage. To improve hologram quality at large depth ranges, we introduce amplitude projection, a post-processing technique that replaces amplitude components of hologram wavefields at each depth layer while preserving phase. This approach enhances reconstruction fidelity, achieving 27.01 dB PSNR and 0.87 SSIM, surpassing a recent optimized silhouette-masking layer-based method by 2.03 dB and 0.04 SSIM, respectively. We further validate the utility of KOREATECH-CGH through experiments on hologram generation and super-resolution using state-of-the-art ML models, confirming its applicability for training and evaluating next-generation ML-CGH systems.