构建首个大深度范围层式全息数据集，助力3D全息生成模型训练。
A Large-Depth-Range Layer-Based Hologram Dataset for Machine Learning-Based 3D Computer-Generated Holography
- 基于多层深度信息生成跨分辨率全息图，覆盖理论极限深度范围。
- 引入振幅投影后处理，使重建质量达27.01 dB PSNR与0.87 SSIM。
- 数据集支持先进模型训练，适合全息生成与超分辨研究者使用。
近年来，基于机器学习的计算机生成全息（ML-CGH）发展迅速，但受限于高质量、大规模全息数据集的缺乏。为此，我们提出KOREATECH-CGH，一个公开可获取的数据集，包含6,000对RGB-D图像与复数全息图，分辨率从256×256至2048×2048，深度范围扩展至角谱法的理论极限，实现大范围3D场景覆盖。为提升远距离深度下的全息质量，我们引入振幅投影技术，在保留相位的前提下替换各深度层的振幅分量。该方法显著提升重建保真度，达到27.01 dB PSNR与0.87 SSIM，较近期最优的轮廓掩码层方法分别提升2.03 dB与0.04 SSIM。我们通过前沿ML模型在全息生成与超分辨任务上的实验，验证了该数据集在训练与评估下一代ML-CGH系统中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。