End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration

• URL: http://arxiv.org/abs/2603.18554v1
• Date: Thu, 19 Mar 2026 07:09:24 GMT
• Title: End-to-End QGAN-Based Image Synthesis via Neural Noise Encoding and Intensity Calibration
• Abstract summary: Quantum Generative Adversarial Networks (QGANs) offer a promising path for learning data distributions on near-term quantum devices.<n>Existing QGANs for image synthesis avoid direct full-image generation, relying on classical post-processing or patch-based methods.<n>We propose ReQGAN, an end-to-end framework that synthesizes an entire N=2D-pixel image using a single D-qubit quantum circuit.
• Score: 13.610834459583344
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation [14.668365971999515]
  Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits.<n>Existing amplitude-based approaches face two key limitations: pixel locations are encoded by computational-basis indices or address qubits.<n>We reformulate quantum image generation as coordinate-conditioned implicit function learning.
  arXiv  Detail & Related papers  (2026-08-12T10:10:22Z)
• SQGen: Structured Quantum Image Generation with Latent-Modulated Quantized Tensor Trains [34.589572571878215]
  We propose SQGen, a full quantum generator built on a quantized tensor train (QTT) with a latent modulation architecture.<n>Experiments on image datasets and synthetic data demonstrate that SQGen trains stably, generates images end-to-end from a shallow circuit with no classical decoder.
  arXiv  Detail & Related papers  (2026-07-07T09:33:18Z)
• Resource-Efficient Quantum-Enhanced Compressive Imaging via Quantum Classical co-Design [0.0]
  Quantum sensing can enhance imaging performance by reducing measurement noise below the classical limit.<n>In conventional quantum imaging schemes, squeezing is applied independently to each pixel or spatial mode.<n>We show that integrating quantum resource allocation with the guidance from classical compressive imaging, via co-design between the quantum hardware layer and the classical software layer, substantially reduces the required quantum resources.
  arXiv  Detail & Related papers  (2026-04-17T19:41:24Z)
• Quantum Implicit Neural Representations for 3D Scene Reconstruction and Novel View Synthesis [42.138439537056954]
  Implicit neural representations (INRs) have become a powerful paradigm for continuous signal modeling and 3D scene reconstruction.<n>We present Quantum Neural Radiance Fields (Q-NeRF), the first hybrid quantum-classical framework for neural radiance field rendering.
  arXiv  Detail & Related papers  (2025-12-14T13:24:11Z)
• Universal super-resolution framework for imaging of quantum dots [4.842569392617605]
  We present a universal deep-learning method that reconstructs super-resolved images of quantum emitters from a single camera frame measurement.<n>We validate the approach on low- and high-density In(Ga)As quantum dots and strain-induced dots in 2D monolayer WSe$$, resolving overlapping emitters even under low signal-to-noise and inhomogeneous backgrounds.
  arXiv  Detail & Related papers  (2025-10-07T16:01:41Z)
• 2D Gaussian Splatting with Semantic Alignment for Image Inpainting [46.266955851252504]
  We propose the first image inpainting framework based on 2D Gaussian Splatting.<n>For global semantic consistency, we incorporate features from a pretrained DINO model.<n>Our method achieves competitive performance in both quantitative metrics and perceptual quality.
  arXiv  Detail & Related papers  (2025-09-02T05:12:52Z)
• Quantum Visual Fields with Neural Amplitude Encoding [70.86293548779774]
  We introduce a new type of Quantum Implicit Neural Representation (QINR) for 2D image and 3D geometric field learning.<n>QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold.<n>Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space.
  arXiv  Detail & Related papers  (2025-08-14T17:59:52Z)
• A Quantum Range-Doppler Algorithm for Synthetic Aperture Radar Image Formation [47.1482540145286]
  We show how in general reference functions, a key element in many SAR focusing algorithms, can be mapped to quantum gates.<n>We find that the core of the quantum range-Doppler algorithm has a computational complexity $O(N)$, less than its classical counterpart.
  arXiv  Detail & Related papers  (2025-04-29T14:24:23Z)
• End-to-End Demonstration of Quantum Generative Adversarial Networks for Steel Microstructure Image Augmentation on a Trapped-Ion Quantum Computer [1.6459866832540102]
  Generative adversarial networks (GANs) are a machine learning technique capable of producing high-quality synthetic images.<n>We integrate quantum computing with GANs to generate complex 5-channel electron backscatter diffraction (EBSD) images of two distinct microstructure phases of steel.<n>We find that the hybrid quantum-classical WGAN improves over classical Bernoulli GANs in 70% of samples.
  arXiv  Detail & Related papers  (2025-04-11T17:55:58Z)
• HQViT: Hybrid Quantum Vision Transformer for Image Classification [48.72766405978677]
  We propose a Hybrid Quantum Vision Transformer (HQViT) to accelerate model training while enhancing model performance.<n>HQViT introduces whole-image processing with amplitude encoding to better preserve global image information without additional positional encoding.<n>Experiments across various computer vision datasets demonstrate that HQViT outperforms existing models, achieving a maximum improvement of up to $10.9%$ (on the MNIST 10-classification task) over the state of the art.
  arXiv  Detail & Related papers  (2025-04-03T16:13:34Z)
• Image Denoising with Machine Learning: A Novel Approach to Improve Quantum Image Processing Quality and Reliability [3.8704324110545767]
  Quantum Image Processing (QIP) aims to utilize the benefits of quantum computing for manipulating and analyzing images. QIP faces two challenges: the limitation of qubits and the presence of noise in a quantum machine. We propose a novel approach to address the issue of noise in QIP by training and employing a machine learning model that identifies and corrects the noise in quantum-processed images.
  arXiv  Detail & Related papers  (2024-02-18T16:55:54Z)
• A quantum segmentation algorithm based on local adaptive threshold for NEQR image [7.798738743268923]
  The complexity of our algorithm can be reduced to $O(n2+q)$, which is an exponential speedup compared to the classic counterparts. The experiment is conducted on IBM Q to show the feasibility of our algorithm in the noisy intermediate-scale quantum (NISQ) era.
  arXiv  Detail & Related papers  (2023-10-02T04:01:42Z)
• Simulation of Entanglement Generation between Absorptive Quantum Memories [56.24769206561207]
  We use the open-source Simulator of QUantum Network Communication (SeQUeNCe), developed by our team, to simulate entanglement generation between two atomic frequency comb (AFC) absorptive quantum memories. We realize the representation of photonic quantum states within truncated Fock spaces in SeQUeNCe. We observe varying fidelity with SPDC source mean photon number, and varying entanglement generation rate with both mean photon number and memory mode number.
  arXiv  Detail & Related papers  (2022-12-17T05:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.