Image and Signal Denoising Methods

Neueste Paper

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

  Cristian Comellas, Julia Navarro, Antoni Buades · 25. September 2026

  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. …

• Adaptive double-phase Rudin--Osher--Fatemi denoising model

  Wojciech G\'orny, Micha{\l} {\L}asica, Alexandros Matsoukas · 24. September 2026

  Even though more than 30 years have passed since the seminal Rudin--Osher--Fatemi (ROF) paper on total variation (TV) denoising, it remains relevant due to its simplicity, robustness and interpretability. However, it is known to suffer from artifacts such as the staircasing effect. Many variants of …

• Image Denoising Using Lower Semi-Frames

  Hemalatha M, P. Sam Johnson · 24. September 2026

  A blind image denoising framework based on an infinite directional lower semi-frame (DLSF) is proposed for additive white Gaussian noise. The model employs scale-dependent directional analysis with resolvent regularization of the unbounded semi-frame operator. Noise variance is estimated directly in…

• Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising

  Dingyan Shang, Zhenyu Xu, Youting Wang, Bonan Shen, Bowen Liu · 16. September 2026

  Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectures about why the L1 loss outperforms L2 here. First, the hypothesis that the L1 loss confers robustness via parameter sparsity confuses the loss with…

• Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

  Jiayin Chen, Yicheng Xu, Muting Wang · 11. September 2026

  Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digital ripple. We present Mi-Ripple, a diagnosis-guided restoration workflow that suppresses this digital ripple while protecting image structure. Mi-Ripple separates periodic lattice …

• ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation

  Jiarui Liu, Heng Li, Weiyu Li, Keng Deng, Junyuan Deng, Zheng Zhongxing, Junyu Huang, Jiahao Chang, Xiaoguang Han, Ping Tan · 11. September 2026

  Qualitative results and an illustration of our core idea. Top left: reconstruction results on benchmark images. Top right: reconstruction results on real-world images. Bottom: illustration of reconstruction-guided noise initialization and modulation. Given multiple input images, we predict a point c…

• Layerwise Tunable Lifting Scheme for the Convolutional Neural Network

  Abdumannon Yovkochov, An Le, Sungbal Seo, You-Suk Bae, Truong Nguyen · 10. September 2026

  This work introduces a family of tunable lifting schemes for biorthogonal wavelet filter banks. We propose three lifting strategies: low-pass tuning (LS-LayLatt-LP), high-pass tuning (LS-LayLatt-HP), and a sequential lifting scheme that jointly adapts low- and high-frequency branches (LS-LayLatt-Seq…

• ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration

  Jiaqi Zhang, Yiqi Wang, Hongjie Wu, Bohan Guo, Xinan Wang, Zichen Luo, Taotao Cai, Zhi Chen, Mingkai Zheng · 2. September 2026

  Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. However, existing methods typically incorporate measurement constraints through local corrections. Such corrections may disrupt the source-clean endpoint…

• On Tensor-Based PDEs and their Corresponding Variational Formulations with Application to Color Image Denoising

  Freddie {\AA}str\"om, George Baravdish, Michael Felsberg · 25. August 2026

  The case when a partial differential equation (PDE) can be considered as an Euler-Lagrange (E-L) equation of an energy functional, consisting of a data term and a smoothness term is investigated. We show the necessary conditions for a PDE to be the E-L equation for a corresponding functional. This e…

• Targeted Iterative Filtering

  Freddie {\AA}str\"om, Michael Felsberg, George Baravdish, Claes Lundstr\"om · 25. August 2026

  The assessment of image denoising results depends on the respective application area, i.e. image compression, still-image acquisition, and medical images require entirely different behavior of the applied denoising method. In this paper we propose a novel, nonlinear diffusion scheme that is derived …

• Improved denoising diffusion probabilistic models with efficient non-diagonal covariance modeling

  Rui Xia, Ayan Das, Artem Artemev, Andi Zhang, Guillaume Hennequin, Alberto Bernacchia · 25. August 2026

  The sampling process of Denoising Diffusion Probabilistic Models (DDPMs) can be accelerated by leveraging second-order information in the form of approximations to the denoising posterior covariance -- allowing samples of acceptable quality to be produced in fewer but larger sampling steps. Previous…

• Pixel-Space Diffusion via Observation Operators

  Shaojie Guo, Lichen Ma, Haoyang Tong, Yu He, Zipeng Guo, Xiaoan Liu, Feng Yan, Yu Guo, Fei Wang, Junshi Huang, Yan Wang · 25. August 2026

  Pixel-space diffusion models directly model image distributions but remain difficult to optimize. Recent methods alleviate this challenge through target reparameterization, while still relying on a fixed clean-image target throughout denoising. Through empirical analysis, we identify a scale-time mi…

• Denoised Variance-Based Pruning with Optimal Brain Bias Compensation

  Geon Tack Lee, Jaegul Choo, Kang Eun Jeon · 19. August 2026

  Vision Transformers (ViTs) achieve state-of-the-art performance but carry massive computational overhead that restricts edge deployment. Although structural pruning has emerged as a key strategy to reduce these costs, existing methods often suffer from severe accuracy degradation or require expensiv…

• Image Denoising via the Adaptive Rank-Cluster Filter

  Dmitry Pozdnyakov · 18. August 2026

  A spatial-local image-denoising filter is proposed, and its performance metrics are evaluated in comparison with baseline filtering algorithms, including the median, adaptive median, Gaussian, bilateral, Wiener, anisotropic diffusion, and non-local means. The developed filter is based on aligning th…

• Fidelity-Constrained Anchoring for Black-Box Denoisers

  Masaki Satoh · 14. August 2026

  We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional computation. The method linearly blends the denoised image with the input and selects the maximum blending factor that satisfies a prescribed local f…

• Efficient Image Restoration with State-Dependent Forward Diffusion

  Ziwei Luo, Fredrik K. Gustafsson, Jens Sj\"olund, Thomas B. Sch\"on · 14. August 2026

  This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based approaches that rely on a coupled forward-backward diffusion scheme, FoD directly learns image restoration through a single forward di…

• Hybrid-LUT: Channel-Aware Hybrid Lookup Table and Filtering for Efficient Image Denoising

  Zhilin Ai, Boyu Li, Sidi Yang, Wenqing Shi, Wenyong Zhou, Binxiao Huang, Chenchen Ding, Ngai Wong · 13. August 2026

  Lookup table (LUT)-based image denoising methods have attracted increasing attention due to their high efficiency and hardware-friendly properties. However, existing RGB-LUT approaches require three identical LUTs to process RGB channels in parallel, resulting in large on-chip SRAM consumption. A si…

• ENCORE: Efficient Noise Context-Aware Representation for Low-Dose CT Denoising

  Minwoo Yu, N. Robert Bennett, Jongduk Baek, Adam S. Wang · 12. August 2026

  While deep learning-based denoising has become widely adopted in low-dose CT, conventional models use generic architectures designed for natural images, failing to account for non-stationary and spatially correlated CT noise characteristics. To address this, we propose an Efficient Noise COntext-awa…

• SegDem: Segmentation helps Demosaicing

  Ping Chen, Xiangming Wang, Yongyong Chen, Jiezhang Cao, Kai Zhang, Jingyong Su, Jie Liu, Haijin Zeng · 11. August 2026

  Image demosaicing reconstructs a full-color image from incomplete color measurements produced by a sensor covered with a color filter array (CFA). Most existing methods formulate demosaicing as pixel-level reconstruction and mainly rely on local textures, cross-channel correlations, and low-level im…

• Structural Guidance for Unified Joint Demosaicing and Denoising

  Qixin Zheng, Ping Chen, Qiangqiang Shen, Haijin Zeng · 10. August 2026

  Joint demosaicing and denoising is a fundamental step in camera image signal processing, yet remains challenging because different Bayer-like color filter arrays (CFAs) and sensor noise jointly corrupt both color sampling and image content. Existing unified restoration networks explicitly model CFA …

• PRISM: Principled Reference Identification for Schrodinger Bridge Model

  Forouzan Fallah, Yezhou Yang · 10. August 2026

  Schr\"odinger bridge models restore a clean signal from a degraded observation by following the conditional bridges of a reference process, yet this reference is chosen heuristically, typically white noise with a hand-tuned schedule. We develop PRISM, a theory of bridge reference design. We characte…

• LiteKD-Net: Lightweight Knowledge-Distilled Network for Mobile Image Denoising

  Zhou Zhiyi · 7. August 2026

  Mobile image denoising requires both good restoration quality and low computational cost. In addition, it's annoying to collect large-scale LQ-GT clean pairs. As a result, we propose LiteKD-Net, a lightweight knowledge-distilled network for mobile image denoising. First, a physics-guided noise simul…

• A geometry-based deep equilibrium model for image restoration under multiplicative Gamma noise

  Shengkun Yang, Luca Ratti, Zhichang Guo · 6. August 2026

  We propose a deep learning framework for image restoration from images degraded by both multiplicative Gamma noise and blur. Unlike conventional deep equilibrium (DEQ) models that rely on implicit neural regularization, the proposed method learns an explicit and interpretable regularizer parameteriz…

• LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising

  Jintong Hu, Bin Xia, Junlin Liu, Jiayue Liu, Wenming Yang · 28. Juli 2026

  Single-image self-supervised denoising replaces unavailable clean targets with surrogate targets constructed from noisy observations. Its effectiveness therefore depends on how closely the surrogate objective remains aligned with supervised denoising, especially when noise is correlated, spatially n…

• Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

  Arghya Sinha, Aditya Banerjee, Trishit Mukherjee, Kunal N. Chaudhury · 28. Juli 2026

  Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising performance and global Lipschitz guarantees is challenging. Existing approaches enforce Lipschitz control only empirically, …