Электронный каталог

Статья

Ryabov, N.V.
Progressive Hybrid Quantum–Classical Generative Adversarial Network for Image Generation / N.V.Ryabov // Физика элементарных частиц и атомного ядра. – 2026. – Т. 57, № 4. – P. 710. – URL: https://www1.jinr.ru/Pepan/v-57-4/Ryabov_ann.pdf.

We propose a progressive training strategy for quantum generative adversarial networks (QGANs) that enables stable image generation from 4 × 4 to 28 × 28 pixels via alpha-blended transitions. The method is built on the QINR-QGAN architecture with parameterized quantum circuits and data re-uploading. Experimental validation on MNIST demonstrates approximately two-fold faster convergence to targetresolution quality while maintaining FID, SSIM, and PSNR metrics



ОИЯИ = ОИЯИ (JINR)2026