2018/06/13 by Zhihao Xia, Ayan Chakrabarti, Xia, Zhihao +1 · 1 citation
Computer Science · Engineering · #Advanced Image Fusion Techniques #Advanced Image Processing Techniques #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Geography #Image (mathematics) #Image and Signal Denoising Methods #Image denoising #Leverage (statistics) #Noise (video) #Noise reduction #Non-local means #Pattern recognition (psychology) #Range (aeronautics) #Train #cs.CV
paper · pdf · doi:10.48550/arxiv.1806.05229
Project page at https://projects.ayanc.org/rpcnn/
openalex publication_date 2018/06/13 · openalex created_date 2018/06/21 · arxiv created 2019/12/10 · arxiv updated 2019/12/11 · openalex updated_date 2026/08/08
Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to regress to clean images from noisy inputs. One recourse is to rely on "internal" image statistics, by searching for similar patterns within the input image itself. In this work, we propose a new method for natural image denoising that trains a deep neural network to determine whether patches in a noisy image input share common underlying patterns. Given a pair of noisy patches, our network predicts whether different sub-band coefficients of the original noise-free patches are similar. The denoising algorithm then aggregates matched coefficients to obtain an initial estimate of the clean image. Finally, this estimate is provided as input, along with the original noisy image, to a standard regression-based denoising network. Experiments show that our method achieves state-of-the-art color image denoising performance, including with a blind version that trains a common model for a range of noise levels, and does not require knowledge of level of noise in an input image. Our approach also has a distinct advantage when training with limited amounts of training data.