---
title: "Multi-View Learning with Context-Guided Receptance for Image Denoising"
authors:
  - "Binghong Chen"
  - "Tingting Chai"
  - "Wei Jiang"
  - "Yuanrong Xu"
  - "Guanglu Zhou"
  - "Xiangqian Wu"
doi: "10.24963/ijcai.2025/86"
url: "https://ijcai.org/proceedings/2025/86"
pdf: "https://ijcai.org/proceedings/2025/0086.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "765-773"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Structural and model-based approaches, knowledge representation and reasoning"
  - "Computer Vision: CV: Machine learning for vision"
  - "Computer Vision: CV: Low-level Vision"
  - "Computer Vision: CV: Representation learning"
---

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

Binghong Chen, Tingting Chai, Wei Jiang, Yuanrong Xu, Guanglu Zhou, Xiangqian Wu

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 765-773. DOI: [10.24963/ijcai.2025/86](https://doi.org/10.24963/ijcai.2025/86)

## 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 (CRWKV) model is proposed, combining enhanced multi-view feature integration with efficient sequence modeling. The Context-guided Token Shift (CTS) mechanism is introduced to effectively capture local spatial dependencies and enhance the model's ability to model real-world noise distributions. Also, 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 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. The code is publicly available at https://github.com/Seeker98/CRWKV.