Fast, nonlocal and neural: a lightweight high quality solution to image denoising

• URL: http://arxiv.org/abs/2403.03488v1
• Date: Wed, 6 Mar 2024 06:12:56 GMT
• Title: Fast, nonlocal and neural: a lightweight high quality solution to image denoising
• Authors: Yu Guo, Axel Davy, Gabriele Facciolo, Jean-Michel Morel, Qiyu Jin
• Abstract summary: convolutional neural networks (CNNs) are now outperformed by model based denoising algorithms. We propose a solution by combining a nonlocal algorithm with a lightweight residual CNN. Our solution is between 10 and 20 times faster than CNNs with equivalent performance and attains higher PSNR.
• Score: 19.306450225657414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the widespread application of convolutional neural networks (CNNs), the traditional model based denoising algorithms are now outperformed. However, CNNs face two problems. First, they are computationally demanding, which makes their deployment especially difficult for mobile terminals. Second, experimental evidence shows that CNNs often over-smooth regular textures present in images, in contrast to traditional non-local models. In this letter, we propose a solution to both issues by combining a nonlocal algorithm with a lightweight residual CNN. This solution gives full latitude to the advantages of both models. We apply this framework to two GPU implementations of classic nonlocal algorithms (NLM and BM3D) and observe a substantial gain in both cases, performing better than the state-of-the-art with low computational requirements. Our solution is between 10 and 20 times faster than CNNs with equivalent performance and attains higher PSNR. In addition the final method shows a notable gain on images containing complex textures like the ones of the MIT Moire dataset.

Related papers

• Decoupled Mixup for Generalized Visual Recognition [71.13734761715472]
  We propose a novel "Decoupled-Mixup" method to train CNN models for visual recognition. Our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions to train CNN models. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts.
  arXiv  Detail & Related papers  (2022-10-26T15:21:39Z)
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding [67.33850633281803]
  We present a versatile new input encoding that permits the use of a smaller network without sacrificing quality. A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through a gradient descent. We achieve a combined speed of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds.
  arXiv  Detail & Related papers  (2022-01-16T07:22:47Z)
• Learning from Images: Proactive Caching with Parallel Convolutional Neural Networks [94.85780721466816]
  A novel framework for proactive caching is proposed in this paper. It combines model-based optimization with data-driven techniques by transforming an optimization problem into a grayscale image. Numerical results show that the proposed scheme can reduce 71.6% computation time with only 0.8% additional performance cost.
  arXiv  Detail & Related papers  (2021-08-15T21:32:47Z)
• Content-Aware Convolutional Neural Networks [98.97634685964819]
  Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
  arXiv  Detail & Related papers  (2021-06-30T03:54:35Z)
• Variational Deep Image Denoising [26.77629755630694]
  Convolutional neural networks (CNNs) have shown outstanding performance on image denoising with the help of large-scale datasets. We propose a novel Bayesian framework based on the variational approximation of objective functions.
  arXiv  Detail & Related papers  (2021-04-02T10:10:11Z)
• Deep Universal Blind Image Denoising [26.77629755630694]
  Deep convolutional neural networks (CNNs) have shown great success in image denoising by incorporating large-scale synthetic datasets. We present a CNN-based method that leverages the advantages of both methods based on the Bayesian perspective.
  arXiv  Detail & Related papers  (2021-01-18T11:49:21Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
  We present a framework that models camera imaging pipeline in forward and reverse directions. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-17T15:20:25Z)
• Gated Texture CNN for Efficient and Configurable Image Denoising [6.09170287691728]
  Convolutional neural network (CNN)-based image denoising methods estimate the noise component contained in a noisy input image and restore a clean image by subtracting the estimated noise from the input. Previous denoising methods tend to remove high-frequency information (e.g., textures) from the input. We propose a gated texture CNN (GTCNN), which is designed to carefully exclude the texture information from each intermediate feature map of the CNN by incorporating gating mechanisms. Our GTCNN state-of-the-art performance with 4.8 times fewer parameters than previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-03-16T06:37:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.