SOURCE-LINKED INTELLIGENCE

Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

This work introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting. Among the proposed architectures, the diagonal quantum Fourier transform (QFT) relaxation is invertible with $O(N^2 \log N)$ computational cost for $N\times N$ images, inherently preserving minimum coherence throughout training via its circuit structure and eliminating the need for explicit coherence penalties. Unconstrained gradient-based phase optimization (Riemannian-optimization free) enables efficient learning from randomly sampled training data, allowing the learned transform to ge

Read original source ↗ Open in workspace

recordType

paper

region

Global