Metraipolis › archive › dc_02380287cdde

C$^{2}$-INR: Customized Convolutional Implicit Neural Representation — arXiv:2609.22807

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.22807
License (as archived): CC0-1.0
Archived: 2026-10-09T21:59:17.796Z
SHA-256 of the archived text: b1b437ae7d4e1c44bc6818b5ffb0413b25f99efdf12910b60d2d09dcdc5321b4
Stable URL of this page: https://metraipolis.com/documento/dc_02380287cdde

How to cite

C$^{2}$-INR: Customized Convolutional Implicit Neural Representation — arXiv:2609.22807 — arXiv (en), https://arxiv.org/abs/2609.22807 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02380287cdde (Metraipolis archive dc_02380287cdde, sha256 b1b437ae7d4e1c44bc6818b5ffb0413b25f99efdf12910b60d2d09dcdc5321b4)

BibTeX

@misc{dc02380287cdde,
  title = {C$^2$-INR: Customized Convolutional Implicit Neural Representation — arXiv:2609.22807},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22807},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02380287cdde; sha256 b1b437ae7d4e1c44bc6818b5ffb0413b25f99efdf12910b60d2d09dcdc5321b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22807. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weights serve as a compact form of the signal itself. Most existing INR methods adopt Multi-Layer Perceptrons (MLPs) as their backbone. Since these models render each pixel independently, they inherently fail to exploit the spatial correlations that exist between neighboring pixels. In contrast,convolutional INRs can process pixels in parallel while inherently accounting for inter-pixel dependencies, making them a more natural fit for representing images. Nevertheless, convolutional INRs remain relatively underexplored, and the majority of them rely on fixed architectural settings, leaving little room for image-specific adaptation. In this paper, we investigate network customization for convolutional INRs. We replace conventional filters with irregular directional kernels, whose allocation is guided by the directional energy in the image spectrum, i.e., directions exhibiting stronger energy are assigned a larger number of kernels, enabling content-tailored convolution settings. These kernels are further reformulated via an orthogonal basis to achieve a superior sparse representation. Moreover, we introduce an annealed Gumbel-Softmax-based mechanism for kernel-level activation function selection, which gives the most suitable activation function for each convolution kernel. Extensive experiments demonstrate that our method, namely C$^{2}$-INR, achieves superior performance against state-of-the-art approaches under comparable parameter budgets across a wide range of image processing tasks, including representation, inpainting, and super-resolution.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.22807 — 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 2026-10-09T21:45:20.816Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).