Metraipolis › archive › dc_ed0d2ad5cb16

Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting — arXiv:2609.17298

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17298
License (as archived)
CC0-1.0
Archived
2026-10-15T22:40:11.834Z
SHA-256 of the archived text
44df26eeee2ec8e992b83e9d251993503365cf608f83db635455eec529461d88
Stable URL of this page
https://metraipolis.com/documento/dc_ed0d2ad5cb16

How to cite

Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting — arXiv:2609.17298 — arXiv (en), https://arxiv.org/abs/2609.17298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed0d2ad5cb16 (Metraipolis archive dc_ed0d2ad5cb16, sha256 44df26eeee2ec8e992b83e9d251993503365cf608f83db635455eec529461d88)
BibTeX
@misc{dced0d2ad5cb16,
  title = {Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting — arXiv:2609.17298},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17298},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed0d2ad5cb16; sha256 44df26eeee2ec8e992b83e9d251993503365cf608f83db635455eec529461d88},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-16 in eess.IV).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.17298 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:18:16.507Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).