PapersSelected

Quantum-Inspired Tensor Networks for Image Inpainting

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

Why we picked it

This paper presents a new method for image inpainting that uses quantum-inspired tensor networks, which could be more efficient than existing methods.

This research paper introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting.

Body

The proposed architectures, specifically the diagonal quantum Fourier transform relaxation, are invertible with O(N^2 log N) computational cost for N x N images.

This approach preserves minimum coherence throughout training and eliminates the need for explicit coherence penalties.

Unconstrained gradient-based phase optimization allows efficient learning from randomly sampled training data, enabling the learned transform to generalize to test images observed through fixed sampling masks.

Numerical tests show that the learned models outperform fixed transforms and per-image optimization while matching the performance of much larger unitary architectures, yet with far fewer parameters.

Original · arXiv cs.LG

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

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 generalize to test images observed through fixed sampling masks. Numerical tests show that the learned models outperform fixed transforms and per-image optimization while matching the performance of much larger unitary architectures, yet with far fewer parameters.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks, tensor networks.

Source attribution: curated from arXiv cs.LG (@Shiwen An, Konstantinos Slavakis).