๐ฌTechnical Deep Dive
Full Specifications [+]
โ๏ธ Nexus Index V2.0
๐ฌ Index Insight
FNI V2.0 for Koreatech Cgh 2048 3.6mu: Semantic (S:0), Authority (A:0), Popularity (P:0), Recency (R:0), Quality (Q:0).
Verification Authority
๐๏ธ Data Preview
Row-level preview not available for this dataset.
Schema structure is shown in the Field Logic panel when available.
๐ Explore Full Dataset โ๐งฌ Field Logic
Schema not yet indexed for this dataset.
Dataset Specification
KOREATECH-CGH
This dataset consists of RGBDโcomplex hologram pairs designed for training machine learningโbased computer-generated holography (ML-CGH) models.
It can be used for tasks such as hologram generation, hologram upscaling, and related applications.
The holograms were generated using a layer-based hologram generation method[arxiv].
Note that this dataset is licensed under the Creative Commons Attribution 4.0 International License Non Commercial (CC BY-NC 4.0).
Dataset Sample
| RGB | Depth |
|---|---|
 |
 |
| Amplitude | Phase |
|---|---|
 |
 |
Data Details
Directory structure
root
โโtest
โ โโamp
โ โโ*.exr
โ โโdepth
โ โโimg
โ โโphs
โโtrain
โ โโamp
โ โโdepth
โ โโimg
โ โโphs
โโvalidation
โโamp
โโdepth
โโimg
โโphsDataset Configuration
| Format | Channels | Resolution | Precision | Range | |
|---|---|---|---|---|---|
| RGB | .exr | 3 | 2048 ร 2048 | fp32 | 0-1 |
| Depth | .exr | 1 | 2048 ร 2048 | fp32 | 0-1 |
| Amplitude | .exr | 3 | 2048 ร 2048 | fp32 | dependent to data |
| Phase | .exr | 3 | 2048 ร 2048 | fp32 | 0-1 |
Hologram Parameters
| Parameter | Value |
|---|---|
| Resolution | 2048 ร 2048 |
| Pixel Pitch | 3.6 ฮผm |
| Wavelength (R,G,B) | 638 nm, 532 nm, 450 nm |
| Physical Extent (H ร W ร D) | 7.3728 mm ร 7.3728 mm ร 81.33446 mm |
Data Splits
| Split | Number of Samples |
|---|---|
| Train | 5,000 |
| Validation | 500 |
| Test | 500 |
Source 3D Models
The RGB-D scenes were generated from 3D meshes obtained from the Google Scanned Objects.
License
ยฉ 2025, SPIN Lab, Korea University of Technology and Education (KOREATECH) and Digital Holography Research Group, Electronics and Telecommunications Research Institute (ETRI)
This dataset is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.
You are free to use, modify, and distribute this work for non-commercial purposes, with proper attribution.
Commercial use is strictly prohibited.
See LICENSE and the official CC BY-NC 4.0 license for full terms.
For inquiries, please contact the corresponding author: [email protected]
Acknowledgements
This work was supported by the National Research Foundation of Korea (NRF) through the Ministry of Education's Basic Science Research Program (Grant 2021R1I1A3048263, 50%) and by the Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by the Korea Government (MSIT) (Grant 2019-0-00001, 50%).
Citation
@misc{lee2025largedepthrangelayerbasedhologramdataset,
title={A Large-Depth-Range Layer-Based Hologram Dataset for Machine Learning-Based 3D Computer-Generated Holography},
author={Jaehong Lee and You Chan No and YoungWoo Kim and Duksu Kim},
year={2025},
eprint={2512.21040},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2512.21040},
}AI Summary: Based on Hugging Face metadata. Not a recommendation.
๐ก๏ธ Dataset Transparency Report
Verified data manifest for traceability and transparency.
๐ Identity & Source
- id
- hf-dataset--spin-lab--koreatech-cgh-2048-3.6mu
- slug
- spin-lab--koreatech-cgh-2048-3.6mu
- source
- huggingface
- author
- Spin Lab
- license
- CC-BY-NC-4.0
- tags
- license:cc-by-nc-4.0, arxiv:2512.21040, region:us
โ๏ธ Technical Specs
- architecture
- null
- params billions
- null
- context length
- null
- pipeline tag
๐ Engagement & Metrics
- downloads
- 16,619
- stars
- 1
- forks
- 0
Free2AITools Constitutional Data Pipeline: Curated disclosure mode active. (V15.x Standard)