2018 MultiScaleResidualNetworkforIma

• (Li et al., 2018) ⇒ Juncheng Li, Faming Fang, Kangfu Mei, and Guixu Zhang. (2018). “Multi-scale Residual Network for Image Super-Resolution.” In: Proceedings of 15th European Conference in Computer Vision (ECCV 2018) - Part VIII.

Subject Headings: Residual Neural Network (ResNet); Deep Residual Neural Network; Multiscale Residual Neural Network (MSRN); Multi-Scale Residual Block.

Cited By

• Google Scholar: ~ 170 Citations, Retrieved: 2021-01-24.

Quotes

Author Keywords

• Super-resolution; Convolutional neural network; Multiscale residual network

Abstract

Recent studies have shown that deep neural networks can significantly improve the quality of single-image super-resolution. Current researches tend to use deeper convolutional neural networks to enhance performance. However, blindly increasing the depth of the network cannot ameliorate the network effectively. Worse still, with the depth of the network increases, more problems occurred in the training process and more training tricks are needed. In this paper, we propose a novel multiscale residual network (MSRN) to fully exploit the image features, which outperform most of the state-of-the-art methods. Based on the residual block, we introduce convolution kernels of different sizes to adaptively detect the image features in different scales. Meanwhile, we let these features interact with each other to get the most efficacious image information, we call this structure Multi-scale Residual Block (MSRB). Furthermore, the outputs of each MSRB are used as the hierarchical features for global feature fusion. Finally, all these features are sent to the reconstruction module for recovering the high-quality image.

3. Proposed Method

(...)

Figure 2. The complete architecture of our proposed model. The network is divided into feature extraction and reconstruction, different color squares represent different operations, the top-right of the picture gives a specific description.

3.1 Multi-scale Residual Block (MSRB)

In order to detect the image features at different scales, we propose multi-scale residual block (MSRB). Here we will provide a detailed description of this structure. As shown in Fig. 3, our MSRB contains two parts: multi-scale features fusion and local residual learning.

Figure 3: The structure of multi-scale residual block (MSRB).

(...)

BibTeX

@inproceedings{2018_MultiScaleResidualNetworkforIma,
  author    = {Juncheng Li and
               Faming Fang and
               Kangfu Mei and
               Guixu Zhang},
  editor    = {Vittorio Ferrari and
               Martial Hebert and
               Cristian Sminchisescu and
               Yair Weiss},
  title     = {Multi-scale Residual Network for Image Super-Resolution},
  booktitle = {Proceedings of 15th European Conference in Computer Vision (ECCV 2018) - Part VIII},
  series    = {Lecture Notes in Computer Science},
  volume    = {11212},
  pages     = {527--542},
  publisher = {Springer},
  year      = {2018},
  url       = {https://doi.org/10.1007/978-3-030-01237-3\_32},
  doi       = {10.1007/978-3-030-01237-3\_32},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2018 MultiScaleResidualNetworkforIma	Juncheng Li Faming Fang Kangfu Mei Guixu Zhang			Multi-scale Residual Network for Image Super-Resolution						2018