Metraipolis › archive › dc_159ad86fe63a
Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains — arXiv:2609.25429
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25429
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:39:05.472Z
- SHA-256 of the archived text
b192ccc49e91ac83cf8d38afe8f52109cd88808566150e9a836055776a8b7ddf- Stable URL of this page
https://metraipolis.com/documento/dc_159ad86fe63a
How to cite
Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains — arXiv:2609.25429 — arXiv (en), https://arxiv.org/abs/2609.25429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_159ad86fe63a (Metraipolis archive dc_159ad86fe63a, sha256 b192ccc49e91ac83cf8d38afe8f52109cd88808566150e9a836055776a8b7ddf)
BibTeX
@misc{dc159ad86fe63a,
title = {Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains — arXiv:2609.25429},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25429},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_159ad86fe63a; sha256 b192ccc49e91ac83cf8d38afe8f52109cd88808566150e9a836055776a8b7ddf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we introduce the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR), an advanced variational paradigm that synergistically integrates coordinate-driven implicit neural networks with an anisotropic, structure-tensor-informed total variation regularizer tailored for resolution-agnostic image super-resolution. Casting the continuous-to-discrete acquisition process into an ill-posed inverse problem framework, our formulation equips a SIREN-architected coordinate network with a dynamic Riemannian metric tensor field D(x). By leveraging its spectral decomposition, the proposed regularizer preferentially directs diffusion parallel to dominant structural contours while penalizing cross-edge dissipation, successfully circumventing the classical staircasing artifacts inherent to scalar total variation schemes. We rigorously prove the well-posedness of this formulation in H^1(Omega) by establishing the existence, uniqueness, and metric stability of the variational minimizer, and realize this via an alternating projected optimization algorithm that decouples network parameter tuning from adaptive tensor field updates. Comprehensive experiments conducted on clinical brain magnetic resonance imaging (MRI) and biomedical transmission electron microscopy confirm substantial quantitative and qualitative improvements, yielding PSNR enhancements reaching +5.05 dB over baseline unregularized INRs and +1.71-2.85 dB over isotropic TV-INR across continuous (non-integer) upsampling factors, alongside remarkable noise robustness up to sigma_eta = 0.10 and monotonic preconditioned convergence behavior. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.25429 — 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 2026-10-08T15:56:18.086Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).