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

2025-05-05

AI Summary

Addressing the challenges of modeling complex noise in real-scene image denoising and the high computational cost of Transformer-based methods, this paper proposes a lightweight and efficient multi-view denoising framework. Our approach introduces three key innovations: (1) a context-guided receptance mechanism enabling linear-complexity, full-pixel interaction; (2) context-guided token shifting (CTS) jointly with bidirectional WKV (BiWKV) to effectively capture long-range dependencies; and (3) a frequency-mixing (FMix) module integrating frequency-domain and spatial-domain modeling to enhance characterization of noise distributions. Extensive experiments on multiple real-world denoising benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches, achieving average PSNR/SSIM gains of 1.2–2.4 dB and 0.015–0.028, respectively, while accelerating inference by up to 40%. Moreover, it exhibits superior detail recovery capability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements

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.

Problem

• Distinguish complex noise patterns in real-world images
• Reduce computational cost of Transformer-based denoising models
• Improve noise distribution modeling via multi-view learning

Innovation

• Context-guided Token Shift captures spatial dependencies
• Frequency Mix module isolates high-frequency noise
• Bidirectional WKV enables linear complexity interactions