To obtain clean images with salient structures from noisy observations, a growing trend in current denoising studies is to seek the help of additional guidance images with high signal-to-noise ratios, which are often acquired in different spectral bands such as near infrared. Although previous guided denoising methods basically require the input images to be well-aligned, a more common way to capture the paired noisy target and guidance images is to exploit a stereo camera system. However, current studies on cross-spectral stereo matching cannot fully guarantee the pixel-level registration accuracy, and rarely consider the case of noise contamination. In this work, for the first time, we propose a guided denoising framework for cross-spectral stereo images. Instead of aligning the input images via conventional stereo matching, we aggregate structures from the guidance image to estimate a clean structure map for the noisy target image, which is then used to regress the final denoising result with a spatially variant linear representation model. Based on this, we design a neural network, called as SANet, to complete the entire guided denoising process. Experimental results show that, our SANet can effectively transfer structures from an unaligned guidance image to the restoration result, and outperforms state-of-the-art denoisers on various stereo image datasets. Besides, our structure aggregation strategy also shows its potential to handle other unaligned guided restoration tasks such as super-resolution and deblurring. The source code is available at https://github.com/lustrouselixir/SANet.

Despite the tremendous advances in denoising techniques, it's still challenging to restore a clean image with salient structures based on one noisy observation, especially at high noise levels. In this work, we propose a frequency-domain guided denoising algorithm to conduct denoising with the help of a well-aligned guidance image. Thanks to their structural correlations, the frequency characteristics of the guidance image can indicate whether the frequency coefficients of the noisy target image are contributed by noise or textures. Therefore, the explicit frequency decomposition enables our denoising model to avoid over-smoothing detailed contents. However, as two input images are usually captured in different fields, their structures are not always consistent. Therefore, we model guided denoising with an optimization problem which considers both the representation model of the guidance image and the fidelity to the noisy target. Further, we design a convolutional neural network, called as FGDNet, to explore the optimal solution. Due to the visual masking phenomenon, human eyes are sensitive to noise in the flat areas, but may not perceive noise around edges or textures. Therefore, we expect to remove as much noise as possible to guarantee the spatial smoothness of flat contents, while also preserving high-frequency structures. Through frequency decomposition, our model can process the low-frequency and high-frequency contents separately. We also adopt a frequency-relevant loss function to train the network. Experimental results show that, compared with state-of-the-art guided and non-guided denoisers, our FGDNet achieves higher denoising accuracy and better visual quality in both flat and texture-rich regions.

Recently, multi-modal image processing has shown its great potential in boosting denoising performance in terms of both accuracy and visual quality. However, current studies generally face the challenge of achieving a good balance between noise removal and detail preservation. In this work, we introduce patch-wise frequency decomposition into convolutional neural networks and propose a novel multi-modal image denoising (MID) algorithm. Integrating the frequency-domain information of images from different modalities, our network first predicts a frequency-relevant residual and then regresses the denoised result using a learnable reconstruction kernel. Benefiting from the distinctive properties of noise and true signals as well as the correlation between multi-modal images in the frequency domain, the proposed algorithm can effectively remove noise and simultaneously reconstruct fine details. Extensive experiments demonstrate the superiority and generalizability of our algorithm over state-of-the-art competing algorithms on various MID tasks, including near-infrared guided RGB image denoising, flash guided no-flash image denoising, and RGB guided depth image denoising. Code is available at https://github.com/liuxw11/FRL.