Metraipolis › archive › dc_be2d205ce67e

A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks — arXiv:2609.29334

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29334
License (as archived): CC0-1.0
Archived: 2026-10-08T06:44:26.363Z
SHA-256 of the archived text: 8ba72df5d613ce871543ee00f6cb8d851a19fe6e4f7948847d477851c04cb19f
Stable URL of this page: https://metraipolis.com/documento/dc_be2d205ce67e

How to cite

A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks — arXiv:2609.29334 — arXiv (en), https://arxiv.org/abs/2609.29334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be2d205ce67e (Metraipolis archive dc_be2d205ce67e, sha256 8ba72df5d613ce871543ee00f6cb8d851a19fe6e4f7948847d477851c04cb19f)

BibTeX

@misc{dcbe2d205ce67e,
  title = {A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks — arXiv:2609.29334},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29334},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be2d205ce67e; sha256 8ba72df5d613ce871543ee00f6cb8d851a19fe6e4f7948847d477851c04cb19f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image denoising remains a fundamental problem in image restoration, with applications in photography, biomedical, and scientific imaging. Modern deep neural networks achieve strong performance by learning powerful image priors, but often rely on large black-box models with limited interpretability. In contrast, DCT-based sliding-window and collaborative filtering methods such as BM3D offer clear algorithmic structure, but depend on handcrafted and non-differentiable operations. This work studies how far such structured collaborative filtering principles can be pushed when reformulated as trainable models. We introduce DeepBM3D, a compact fully differentiable architecture that combines non-local patch grouping, DCT-domain filtering, and multi-stage refinement within a BM3D-inspired pipeline. Lightweight convolutional feature extractors guide patch grouping, while filtering is performed through learned Wiener weights in the DCT domain. Experiments show that DeepBM3D improves over classical and hybrid baselines, remains competitive with FFDNet at low and moderate noise levels, and performs particularly well on repetitive textures.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.29334 — 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 2026-10-08T06:09:29.839Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).