Real Image Denoising With Feature Attention

By Saeed Anwar, Nick Barnes. IEEE International Conference on Computer Vision, 2019

673 citations recorded by the source corpus.

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, its performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of the denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality on three synthetic and four real noisy datasets against 19 state-of-the-art algorithms demonstrate the superiority of our RIDNet.

View Paper: https://www.semanticscholar.org/paper/7f683133908ee1ed4d7055b15dcee1de853810f6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Geometric Back-Projection Network for Point Cloud Classification (2019, background): “, image segmentation [35]–[37], image denoising [38], etc.”
CycleISP: Real Image Restoration via Improved Data Synthesis (2020, methodology): “Compared to the recent best algorithm RIDNet [4], our approach demonstrates the performance gain of 0.”
Data collection and quality challenges in deep learning: a data-centric AI perspective (2021, methodology): “For example, privacy machine There have been some approaches to successfully denoising the natural noise using Sparse Coding [145] and Feature Attention [22], but they are out of the scope of this survey.”
Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, methodology): “the base ViT [9] has 18 billion FLOPs compared to the CNN models [198], [199] with 600 million FLOPs, achieving similar performance to process an image.”
Guided Collaborative Training for Pixel-wise Semi-Supervised Learning (2020, background): “Real image denoising [3,15,50] is a task that devotes to removing the real noise, rather synthetic noise, from an input natural image (Fig.”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, methodology): “We compare Uformer with 8 state-of-the-art denoising methods, including the featurebased BM3D [13] and seven learning-based methods: RIDNet [4], VDN [73], CycleISP [75], NBNet [9], DANet [74], MIRNet [76], and MPRNet [77].”
Spatial-Adaptive Network for Single Image Denoising (2020, unknown): “RIDNet [4] proposed a one-stage denoising network with feature attention for real image denoising.”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, methodology): “Recently, deep learning models [6], [9], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42] make significant advances in image denoising, yielding favorable results than those of the hand-crafted methods.”
Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “Noisy RIDNet [3] DANet [76] CycleISP [77] DeamNet [53] MPRNet [79] DGUNet DGUNet”
Deep Learning on Image Denoising: An overview (2019, unknown): “To deal with unknown real noisy images, a residual structure was utilized to facilitate low-frequency features, and then, an attention mechanism [206] could be applied to extract more potential features from channels [11].”
Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, background): “Method DnCNN BM3D CBDNet* RIDNet* AINDNet* VDN SADNet* DANet+* CycleISP* MIRNet DeamNet* MPRNet DAGL Uformer Restormer Dataset [101] [15] [25] [6] [35] [89] [12] [90] [91] [92] [63] [93] [55] [80] (Ours)”
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment (2020, methodology): “For face restoration, most existing methods typically work in a “non-blind” fashion with specific degradation of prescribed type and intensity, leading to a variety of sub-tasks including super resolution[58][8][34][55], hallucination [47][29], denoising[1][60],”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Noisy CBDNet [39] RIDNet [5] VDN [118] MIRNet (Ours) Reference”
Multi-Stage Progressive Image Restoration (2021, methodology): “Numerous network modules and functional units for image restoration have been developed including recursive residual learning [4, 95], dilated convolutions [4, 81], attention mechanisms [17, 86, 96], dense connections [73, 75, 97], encoder-decoders [7, 13, 43, 65], and generative models [44, 62, 90,”