Spatial-Adaptive Network for Single Image Denoising
- URL: http://arxiv.org/abs/2001.10291v2
- Date: Tue, 14 Jul 2020 02:30:55 GMT
- Title: Spatial-Adaptive Network for Single Image Denoising
- Authors: Meng Chang, Qi Li, Huajun Feng, Zhihai Xu
- Abstract summary: We propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal.
Our method can surpass the state-of-the-art denoising methods both quantitatively and visually.
- Score: 14.643663950015334
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Previous works have shown that convolutional neural networks can achieve good
performance in image denoising tasks. However, limited by the local rigid
convolutional operation, these methods lead to oversmoothing artifacts. A
deeper network structure could alleviate these problems, but more computational
overhead is needed. In this paper, we propose a novel spatial-adaptive
denoising network (SADNet) for efficient single image blind noise removal. To
adapt to changes in spatial textures and edges, we design a residual
spatial-adaptive block. Deformable convolution is introduced to sample the
spatially correlated features for weighting. An encoder-decoder structure with
a context block is introduced to capture multiscale information. With noise
removal from the coarse to fine, a high-quality noisefree image can be
obtained. We apply our method to both synthetic and real noisy image datasets.
The experimental results demonstrate that our method can surpass the
state-of-the-art denoising methods both quantitatively and visually.
Related papers
- Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising [19.08732222562782]
Supervised deep learning has become the method of choice for image denoising.
We show that, contrary to popular belief, denoising networks specialized in the removal of Gaussian noise can be efficiently leveraged in favor of real-world image denoising.
arXiv Detail & Related papers (2024-07-24T16:23:46Z) - Multi-stage image denoising with the wavelet transform [125.2251438120701]
Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information.
We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
arXiv Detail & Related papers (2022-09-26T03:28:23Z) - Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis [148.16279746287452]
We propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block.
For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise.
Experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance.
arXiv Detail & Related papers (2022-03-24T18:11:31Z) - Efficient Deep Image Denoising via Class Specific Convolution [24.103826414190216]
We propose an efficient deep neural network for image denoising based on pixel-wise classification.
The proposed method can reduce the computational costs without sacrificing the performance.
arXiv Detail & Related papers (2021-03-02T10:28:15Z) - Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and
Video Denoising [104.59305271099967]
We present a pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising.
We develop a pixel aggregation network for video denoising to sample pixels across the spatial-temporal space.
Our method is able to solve the misalignment issues caused by large motion in dynamic scenes.
arXiv Detail & Related papers (2021-01-26T13:00:46Z) - Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images [98.82804259905478]
We present Neighbor2Neighbor to train an effective image denoising model with only noisy images.
In detail, input and target used to train a network are images sub-sampled from the same noisy image.
A denoising network is trained on sub-sampled training pairs generated in the first stage, with a proposed regularizer as additional loss for better performance.
arXiv Detail & Related papers (2021-01-08T02:03:25Z) - Efficient Blind-Spot Neural Network Architecture for Image Denoising [4.513547390985147]
We propose a novel fully convolutional network architecture that uses dilations to achieve the blind-spot property.
Our network achieves the performance over the prior work and state-of-the-art results on established datasets.
arXiv Detail & Related papers (2020-08-25T13:48:40Z) - Reconstructing the Noise Manifold for Image Denoising [56.562855317536396]
We introduce the idea of a cGAN which explicitly leverages structure in the image noise space.
By learning directly a low dimensional manifold of the image noise, the generator promotes the removal from the noisy image only that information which spans this manifold.
Based on our experiments, our model substantially outperforms existing state-of-the-art architectures.
arXiv Detail & Related papers (2020-02-11T00:31:31Z) - Variational Denoising Network: Toward Blind Noise Modeling and Removal [59.36166491196973]
Blind image denoising is an important yet very challenging problem in computer vision.
We propose a new variational inference method, which integrates both noise estimation and image denoising.
arXiv Detail & Related papers (2019-08-29T15:54:06Z)
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.