CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation

2026-08-12

AI Summary

Traditional quantum image generation methods are constrained by pixel-position encoding, causing quantum resource requirements to scale with image resolution and inducing probabilistic competition among jointly decoded pixels, which hinders precise control. This work proposes a coordinate-conditioned implicit generation paradigm: the image is modeled as an implicit function driven by spatial coordinates and latent variables, where a classical embedding network generates parameters for a variational quantum circuit. Pixel intensities are obtained independently at each coordinate by evaluating the circuit and measuring the expectation values of dedicated color qubits. This approach decouples resolution from the number of address qubits, circumvents inter-pixel probability normalization constraints, and incorporates structural inductive bias. Experiments demonstrate that the proposed framework achieves superior visual and quantitative performance on two benchmark datasets compared to FRQI, PQWGAN, and classical baselines, using significantly fewer qubits.

Abstract

Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits. Existing amplitude-based approaches face two key limitations: pixel locations are typically encoded by computational-basis indices or address qubits, causing quantum resources to grow with image resolution; meanwhile, jointly decoding many pixels from normalized quantum states introduces probability competition among pixels and limits precise pixel-wise control. To address these issues, we reformulate quantum image generation as coordinate-conditioned implicit function learning. Our method takes spatial coordinates and latent variables as inputs, uses a classical embedding network to generate input-dependent circuit parameters, and evaluates a variational quantum circuit at each coordinate. Pixel intensities are directly obtained from the expectation value of a dedicated color qubit, and a complete image is generated by querying all spatial coordinates. This design decouples image resolution from address-qubit requirements and avoids shared probability-normalization constraints across pixels. We further design a specialized variational quantum circuit to provide structural inductive bias for coordinate-conditioned generation. Simulated experiments on two benchmark datasets show that our method outperforms FRQI-based generation and PQWGAN in visual and quantitative quality while using fewer qubits, and also achieves better generation quality than the corresponding classical baseline.

Problem

• quantum generative adversarial networks
• image generation
• amplitude encoding
• pixel-wise control
• quantum resource scaling

Innovation

• coordinate-conditioned
• quantum implicit representation
• variational quantum circuit
• pixel-wise generation
• quantum generative adversarial network