A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks

arXiv:2609.29334 · cs.CV · Submitted 2026-09-24 · Read on arXiv

cs.CV

Submitted: 2026-09-24

Updated: 2026-09-24

Comments: Preprint submitted to Journal of Mathematical Imaging and Vision (JMIV). 17 pages, 11 figures. Supported by MCIN/AEI/10.13039/501100011033 under grant PID2021-125711OB-I00, and by the Spanish Ministry of Universities under grant FPU24/02805

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: Image denoising remains a fundamental problem in image restoration, with applications in photography, biomedical, and scientific imaging.

Terminology

Abstract

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.

Sources

Related papers