Residual Dense Network for Image Restoration

By Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Raymond Fu. 2018

853 citations recorded by the source corpus.

Recently, deep convolutional neural network (CNN) has achieved great success for image restoration (IR) and provided hierarchical features at the same time. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images; thereby, resulting in relatively-low performance. In this work, we propose a novel and efficient residual dense network (RDN) to address this problem in IR, by making a better tradeoff between efficiency and effectiveness in exploiting the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

SwinIR: Image Restoration Using Swin Transformer (2021, methodology): “Following [98, 88], we test different methods on two benchmark datasets (Classic5 [22] and LIVE1 [67]) for JPEG quality factors 10, 20, 30 and 40.”
Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration (2022, background): “Here, the structure of the dual-path feature extraction module inherits the residual dense network [ Zhang et al. , 2021b ] , and the extracted features are presented by where M θ E is the feature extraction module, and θ E is its parameter.”
Image De-Raining Transformer (2022, background): “In recent years, deep learning are widely used in various image processing tasks [17], [18], [31], [32], [33], [34], [35], such as de-noising [36], [37], [38], super-resolution [39], [40], [41], de-blurring [42], [43], [44], [45], de-hazing [19], [19], [46], [47], [48], [49], [50], low-light image…”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, background): “E-mail: waqas.zamir@inceptioniai.org • S. khan and F.S. Khan the other hand, the high-resolution (single-scale) networks [5], [6], [7], [8] do not employ any downsampling operation, and thereby recover better spatial details.”
Artificial Intelligence for the Metaverse: A Survey (2022, background): “Some other advanced image restoration works exploited CNN architectures to reduce image compression artifacts, restore clean images from downscaled and blurred images, and reconstruct missing details [63]–[65].”
Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, background): “In recent years, data-driven CNN architectures [7, 18, 92, 93, 105, 107] have been shown to outperform conventional restoration approaches [26,36,53,75].”
Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks (2022, background): “In a quick search, it is possible to find a diversity of works using Convolutional Neural Networks, such as image classification [15, 16, 25, 56], object detection [11, 42], and image reconstruction [73–75].”
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,”
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild (2024, background): “The goal of IR is to convert degraded images into high-quality degradation-free images [22, 26, 86, 88, 95, 96].”
High-Quality Self-Supervised Deep Image Denoising (2019, background): “, U-Nets [23], hierarchical residual networks [20], and residual dense networks [31].”
TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (2018, background): “Current state-of-the-art SISR networks [20, 21, 22, 23, 24, 25, 26] trained on the DIV2K and outperformed previous networks by a substantial margin.”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, background): “al-resolution reduction, on the downside, the ne spatial details are lost, making it extremely hard to recover them in the later stages. On the other side, the high-resolution (single-scale) networks [27,120,127,50] do not employ any downsampling operation, and thereby produce images with spatially ”