Proceedings ArticleDOI
IRGUN : Improved Residue Based Gradual Up-Scaling Network for Single Image Super Resolution
Manoj Sharma,Rudrabha Mukhopadhyay,Avinash Upadhyay,Sriharsha Koundinya,Ankit Shukla,Santanu Chaudhury +5 more
- pp 834-843
Reads0
Chats0
TLDR
A novel Improved Residual based Gradual Up-Scaling Network (IRGUN) to improve the quality of the super-resolved image for a large magnification factor and recovers fine details effectively at large (8X) magnification factors.Abstract:
Convolutional neural network based architectures have achieved decent perceptual quality super resolution on natural images for small scaling factors (2X and 4X). However, image super-resolution for large magnication factors (8X) is an extremely challenging problem for the computer vision community. In this paper, we propose a novel Improved Residual based Gradual Up-Scaling Network (IRGUN) to improve the quality of the super-resolved image for a large magnification factor. IRGUN has a Gradual Upsampling and Residue-based Enhancment Network (GUREN) which comprises of series of Up-scaling and Enhancement blocks (UEB) connected end-to-end and fine-tuned together to give a gradual magnification and enhancement. Due to the perceptual importance of the luminance in super-resolution, the model is trained on luminance (Y) channel of the YCbCr image. Whereas, the chrominance components (Cb and Cr) channel are up-scaled using bicubic interpolation and combined with super-resolved Y channel of the image, which is then converted to RGB. A cascaded 3D-RED architecture trained on RGB images is utilized to incorporate its inter-channel correlation. In addition to this, the training methodology is also presented in the paper. In the training procedure, the weights of the previous UEB are used in the next immediate UEB for faster and better convergence. Each UEB is trained on its respective scale by taking the output image of the previous UEB as input and corresponding HR image of the same scale as ground truth to the successive UEB. All the UEBs are then connected end-to-end and fine tuned. The IRGUN recovers fine details effectively at large (8X) magnification factors. The efficiency of IRGUN is presented on various benchmark datasets and at different magnification scales.read more
Citations
More filters
Proceedings ArticleDOI
NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results
TL;DR: This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.
Journal ArticleDOI
Are Recent SISR Techniques Suitable for Industrial Applications at Low Magnification
TL;DR: A fast image upsampling method designed specifically for industrial applications at low magnification that can obtain performance comparable to that of some state-of-the-art methods for 720P-to-1080P magnification, but the computational cost is much lower.
Proceedings ArticleDOI
Going Much Wider with Deep Networks for Image Super-Resolution
TL;DR: This work proposes a divide and conquer approach based wide and deep network (WDN) that divides the 4× up-sampling problem into 32 disjoint subproblems that can be solved simultaneously and independently of each other.
Book ChapterDOI
Gradually Growing Residual and Self-attention Based Dense Deep Back Projection Network for Large Scale Super-Resolution of Image
Manoj Sharma,Avinash Upadhyay,Ajay Pratap Singh,Megh Makwana,Swati Bhugra,Brejesh Lall,Santanu Chaudhury,Deepak,Anil Kumar Saini +8 more
TL;DR: A novel light-weight architecture-Gradually growing Residual and self-Attention based Dense Deep Back Projection Network (GRAD-DBPN) for large scale image super-resolution (SR) and overcomes the issue of vanishing gradient.
Exploiting Cross-Modal Redundancy for Audio-Visual Generation
TL;DR: This work proposes a new paradigm for speech enhancement: “pseudo-visual” approach, where the visual stream is synthetically generated from the noisy speech input, and demonstrates that the robustness and the accuracy boost obtained from the model lead to various real-world applications which were previously not possible.
References
More filters
Journal ArticleDOI
GUN: Gradual Upsampling Network for Single Image Super-Resolution
TL;DR: Wang et al. as mentioned in this paper proposed a gradual upsampling network (GUN), which consists of an input layer, multiple upsamplings and convolutional layers, and an output layer.
Journal ArticleDOI
High Resolution Local Structure-Constrained Image Upsampling
TL;DR: A fast and efficient image upsampling method that makes use of high-resolution local structure constraints that recovered finer pixel-level texture details and obtained top-level objective performance with a low time cost compared with state-of-the-art methods.
Proceedings ArticleDOI
Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning
TL;DR: In this article, a GAN-based architecture using densely connected convolutional neural networks (DenseNets) was proposed to super-resolve overhead imagery with a factor of up to 8x.
Proceedings ArticleDOI
Deep learning based frameworks for image super-resolution and noise-resilient super-resolution
TL;DR: Experimental results show that proposed noise resilient super-resolution framework outperforms the conventional and state-of-the-art approaches in terms of PSNR and SSIM metrics.