Jul 2026· International Conference on Signal Processing and Communications· pp. 1-5· 0 citations· 27 references
Abstract
Without noise, image processing and pattern recognition would be a fait accompli! Image denoising remains a fundamental challenge in practical image processing applications. Deep neural networks (DNNs) have set new performance benchmarks over classical techniques by using supervised learning to predict either the clean image or the noise exclusively. This paper brings both paradigms on the same footing and examines them from the minimum meansquared error (MMSE) estimation perspective, which requires that their outputs must satisfy a linear constraint, referred to as the consistency criterion. We show that jointly optimizing the image prediction and noise prediction models by enforcing the consistency criterion bridges the gap between the two paradigms and improves denoising performance across multiple settings. Experiments show up to 0.49 dB Peak Signal-to-Noise Ratio (PSNR) gain on CBSD68, Kodak24, McMaster, Urban100 datasets, and 0.46 dB on SIDD dataset, across diverse architectures like DnCNN, SwinIR, CycleISP, and Restormer, under both synthetic and real-world noise.
Real-world images are often noisy. Noises may come from sensor limitations, low illuminations, and other factors. Regardless of the sources, noises degrade image's quality and often affect the accuracy of later analysis in computer vision. To solve this, various denoising methods have been proposed. However, many of th...
Kok Swee Sim, Iksan Bukhori, Mahda Laina Arnumukti et al.· International Conference on...· 0 citations
Computer vision technologies are increasingly used across Oil and Gas operations to support inspection, monitoring, and surveillance tasks. In industrial environments, however, image quality is often degraded by lens-induced optical distortions and environmental noise arising from low illumination, dust, vibration, a...
Maria A. Alghamdi, Fatimah A. AlYousif, Amani M. Barsheed· GOTECH· 0 citations
Image denoising aims to restore clean, high-fidelity visual structures from noisy inputs. Although deep learning (DL) approaches have dominated state-of-the-art benchmarks, they often incur heavy computational overhead, massive parameter counts, and a lack of mathematical transparency. To tackle these limitations, we p...
Li-Heng Wang, Yi-Xing Wu, Wei Wang et al.· Applications of Digital Imag...· 0 citations
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-bas...
C. Comellas, Julia Navarro, A. Buades· 0 citations
Deep image denoisers achieve strong performance on synthetic additive white Gaussian noise (AWGN), but under heavy noise they often oversmooth edges and destabilize fine textures. Existing gradient-and frequency-based regularization can improve detail preservation, yet uniformly enforcing such constraints may over-regu...
Deng-Feng Qiao· 2026 7th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
