Multi-View Learning with Context-Guided Receptance for Image Denoising

TL;DR

This paper introduces a novel multi-view learning model with context-guided receptance for image denoising, combining frequency-domain features and efficient sequence modeling to outperform state-of-the-art methods in real-world noise reduction.

Contribution

The proposed Context-guided Receptance Weighted Key-Value ( extbackslash M) model innovatively integrates multi-view features, frequency-domain analysis, and efficient Bidirectional WKV mechanism for improved denoising performance.

Findings

Outperforms existing state-of-the-art denoising methods on multiple datasets.

Reduces inference time by up to 40%.

Effectively restores fine details in noisy images.

Abstract

Image denoising is essential in low-level vision applications such as photography and automated driving. Existing methods struggle with distinguishing complex noise patterns in real-world scenes and consume significant computational resources due to reliance on Transformer-based models. In this work, the Context-guided Receptance Weighted Key-Value (\M) model is proposed, combining enhanced multi-view feature integration with efficient sequence modeling. Our approach introduces the Context-guided Token Shift (CTS) paradigm, which effectively captures local spatial dependencies and enhance the model's ability to model real-world noise distributions. Additionally, the Frequency Mix (FMix) module extracting frequency-domain features is designed to isolate noise in high-frequency spectra, and is integrated with spatial representations through a multi-view learning process. To improve computational efficiency, the Bidirectional WKV (BiWKV) mechanism is adopted, enabling full pixel-sequence interaction with linear complexity while overcoming the causal selection constraints. The model is validated on multiple real-world image denoising datasets, outperforming the existing state-of-the-art methods quantitatively and reducing inference time up to 40\%. Qualitative results further demonstrate the ability of our model to restore fine details in various scenes.