JSE0/SOQ-NRC

---
license: other
license_name: soq-nrc-research-license-v1.0
license_link: LICENSE
size_categories:
- 100B<n<1T
---

# SOQ-NRC (Subjective and Objective Quality Evaluation of Numerical Reconstructions from Compressed Holograms)

This dataset consists of NR-domain images obtained by applying DRUNet, NNPF, and the proposed network to each VTM-decoded hologram sequence, and corresponds to the dataset used for subjective quality assessment in [our paper](). (To be updated)

## Introduction

Digital hologram compression introduces distortions that become perceptually visible after numerical reconstruction (NR). Evaluating quality directly in the NR spatial domain is therefore essential for understanding perceptual degradation.

The **SOQ-NRC** dataset provides NR-domain images generated from VTM-compressed holograms. Each decoded hologram sequence is processed using DRUNet, NNPF, and the proposed network to produce NR images with diverse distortion levels. Multiple QP settings are selected to cover a range of compression severities.

By providing NR images along with corresponding Mean Opinion Scores (MOS), **SOQ-NRC** serves as a benchmark dataset for subjective quality assessment, restoration comparison, and perceptual analysis of compression artifacts in holographic imaging systems.

## Dataset Details and Structure

The **SOQ-NRC** dataset includes 6 original holographic images in NR domain. A summary of the **SOQ-NRC** dataset is provided in the table below.

| Type | CTC | Hologram | Resolution | Pixel Pitch | Wavelength | Propagation Method | Selected QP |
|------|-----|-----------------|---------------------|---------------------|-------------|--------|--------------|
| CGH | ✓ | Piano16k | 16384×16384 | 0.4e-6 | 640e-9, 532e-9, 473e-9 | ASM | 35, 38, 41 |
| CGH | ✓ | SpecularCar16k | 16384×16384 | 0.4e-6 | 640e-9, 532e-9, 473e-9 | ASM | 32, 35, 38 |
| OCH | ✓ | Lowiczanka Doll | 59394×2016 | 3.45e-6 | 637e-9, 532e-9, 457e-9 | Fourier-Fresnel | 35, 38, 41 |
| CGH | ✗ | Piano8k | 8192×8192 | 0.4e-6 | 640e-9, 532e-9, 473e-9 | ASM | 35, 38, 41 |
| CGH | ✗ | Ring4k | 4096×4096 | 0.4e-6 | 640e-9, 532e-9, 473e-9 | ASM | 27, 32, 35 |
| CGH | ✗ | DiffuseCar4k | 4096×4096 | 0.4e-6 | 640e-9, 532e-9, 473e-9 | ASM | 27, 32, 35 |

The **SOQ-NRC** dataset provides NR-domain images generated from VTM-compressed holograms.
For each hologram sequence, multiple compression levels are selected using representative quantization parameters (QPs).
The decoded holograms are filtered using DRUNet, NNPF, and the proposed network, and the resulting numerically reconstructed images are included for subjective quality assessment.

The dataset structure is as follows:

- **NR Images (153.08 GB)**
- Contains numerically reconstructed spatial-domain images used for subjective quality evaluation. Images are grouped by hologram sequence.
- Includes *Piano16k*, *SpecularCar16k*, *Lowicznka Doll*, *Piano8k*, *Ring4k*, and *DiffuseCar4k*.
- **MOS Data**
- Contains the Mean Opinion Scores (MOS) obtained from subjective experiments. Scores correspond to the NR-domain images and are indexed by sequence, QP, and filtering method (DRUNet, NNPF, Proposed).
- Includes evaluation results for *Piano16k*, *SpecularCar16k*, *Lowicznka Doll*, *Piano8k*, *Ring4k*, and *DiffuseCar4k*.

### Dataset Sources

We provide processed versions of the holographic images supplied by **B<>com**. The specifications of the original holograms are summarized below.

- **Repository:** [B<>com Hologram Repository](https://hologram-repository.labs.b-com.com/#/holographic-images)
- **Reference Papers:**
- A. Gilles, P. Gioia, R. Cozot, and L. Morin, "Hybrid approach for fast occlusion processing in computer-generated hologram calculation," Appl. Opt., AO, vol. 55, no. 20, pp. 5459-5470, Jul. 2016.
- A. Gilles, P. Gioia, R. Cozot, and L. Morin, "Computer generated hologram from Multiview-plus-Depth data considering specular reflections," in 2016 IEEE International Conference on Multimedia Expo Workshops (ICMEW), 2016, pp. 1-6.

Numerical reconstruction (NR) is performed with the Numerical Reconstruction Software for Holography (NRSH) version 16.0.
- **Reference:** [ISO/IEC JTC 1/SC29/WG1 N100837, PCQ "Numerical Reconstruction Software for Holography (NRSH) v16.0](https://ds.jpeg.org/documents/jpegpleno/wg1n100837-103-PCQ-Numerical_Reconstruction_Software_for_Holography_v16_0.zip)

### Copyright Notice

This dataset and resources are provided by the **Intelligent Visual Media Laboratory (IVML)** and are intended for **research and academic use only**.
By using this dataset, you agree to cite our paper "**ROI-guided Dual-domain Network for Enhanced Numerical Reconstruction of Compressed Holograms**" in any publications or presentations that utilize this dataset.

- **Copyright:** **Copyright (c) 2026 Intelligent Visual Media Laboratory (IVML)** The VTM-FCH dataset is copyrighted by the Intelligent Visual Media Laboratory (IVML). All rights are reserved. Unauthorized use, reproduction, or distribution of this dataset, or any portion thereof, is strictly prohibited without prior written permission from IVML. For any inquiries regarding the dataset, please contact us at [e-mail]. Permission is not granted, without written agreement and without license or royalty fees, to use, copy, modify, and distribute this dataset and its documentation for any purpose.
- **Acknowledgment:** This work was supported by the National Research Foundation of Korea (NRF) funded by Korean Government [Ministry of Science and ICT (MSIT)] under Grant RS-2023-00250751.

## Contact

For questions or requests regarding the dataset, please contact:

- Juyeon Seo, [e-mail]
- Hyeji Jang, [e-mail]