End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915874360786944 |
|---|---|
| author | Yang, Xue Zhou, Rigui Jia, Shizheng Koh, Dax Enshan Goh, Siong Thye Li, Yaochong Chen, Hongyu Xiong, Fuhui |
| author_facet | Yang, Xue Zhou, Rigui Jia, Shizheng Koh, Dax Enshan Goh, Siong Thye Li, Yaochong Chen, Hongyu Xiong, Fuhui |
| contents | Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices. However, existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods. These approaches dilute the quantum generator's role and struggle to capture global image semantics. To address this, we propose ReQGAN, an end-to-end framework that synthesizes an entire N=2^D-pixel image using a single D-qubit quantum circuit. ReQGAN overcomes two fundamental bottlenecks hindering direct pixel generation: (1) the rigid classical-to-quantum noise interface and (2) the output mismatch between normalized quantum statistics and the desired pixel-intensity space. We introduce a learnable Neural Noise Encoder for adaptive state preparation and a differentiable Intensity Calibration module to map measurements to a stable, visually meaningful pixel domain. Experiments on MNIST and Fashion-MNIST demonstrate that ReQGAN achieves stable training and effective image synthesis under stringent qubit budgets, with ablation studies verifying the contribution of each component. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18554 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration Yang, Xue Zhou, Rigui Jia, Shizheng Koh, Dax Enshan Goh, Siong Thye Li, Yaochong Chen, Hongyu Xiong, Fuhui Quantum Physics Computer Vision and Pattern Recognition Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices. However, existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods. These approaches dilute the quantum generator's role and struggle to capture global image semantics. To address this, we propose ReQGAN, an end-to-end framework that synthesizes an entire N=2^D-pixel image using a single D-qubit quantum circuit. ReQGAN overcomes two fundamental bottlenecks hindering direct pixel generation: (1) the rigid classical-to-quantum noise interface and (2) the output mismatch between normalized quantum statistics and the desired pixel-intensity space. We introduce a learnable Neural Noise Encoder for adaptive state preparation and a differentiable Intensity Calibration module to map measurements to a stable, visually meaningful pixel domain. Experiments on MNIST and Fashion-MNIST demonstrate that ReQGAN achieves stable training and effective image synthesis under stringent qubit budgets, with ablation studies verifying the contribution of each component. |
| title | End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration |
| topic | Quantum Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.18554 |