Corpus ID: 237292756

Efficient Transformer for Single Image Super-Resolution

  title={Efficient Transformer for Single Image Super-Resolution},
  author={Zhisheng Lu and Hong Liu and Juncheng Li and Linlin Zhang},
  • Zhisheng Lu, Hong Liu, +1 author Linlin Zhang
  • Published 2021
  • Computer Science
  • ArXiv
Single image super-resolution task has witnessed the great strides with the development of deep learning. However, most existing studies focus on building a more complex neural network with a massive number of layers, bringing heavy computational cost and memory storage. Recently, as Transformer yields brilliant results in NLP tasks, more and more researchers start to explore the application of Transformer in computer vision tasks. But with the heavy computational cost and high GPU memory… Expand
2 Citations
From Beginner to Master: A Survey for Deep Learning-based Single-Image Super-Resolution
This survey gives an overview of DL-based SISR methods and group them according to their targets, such as reconstruction efficiency, reconstruction accuracy, and perceptual accuracy, as well as introducing some related works, including benchmark datasets, upsampling methods, optimization objectives, and image quality assessment methods. Expand
Transformers in Vision: A Survey
This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. Expand


Fast and Accurate Single Image Super-Resolution via Information Distillation Network
This work proposes a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image and demonstrates that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance. Expand
Lightweight Image Super-Resolution with Information Multi-distillation Network
An adaptive cropping strategy (ACS) is developed to super-resolve block-wise image patches using the same well-trained model and performs favorably against the state-of-the-art SR algorithms in terms of visual quality, memory footprint, and inference time. Expand
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
A computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR that outperforms SOTA methods for all scales, which proves its ability to better utilize the auxiliary features. Expand
Accelerating the Super-Resolution Convolutional Neural Network
This paper aims at accelerating the current SRCNN, and proposes a compact hourglass-shape CNN structure for faster and better SR, and presents the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. Expand
Pre-Trained Image Processing Transformer
To maximally excavate the capability of transformer, the IPT model is presented to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs and the contrastive learning is introduced for well adapting to different image processing tasks. Expand
Learning with Privileged Information for Efficient Image Super-Resolution
This paper introduces a novel distillation framework, consisting of teacher and student networks, that allows to boost the performance of FSRCNN drastically, and proposes to use ground-truth high-resolution (HR) images as privileged information. Expand
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
This paper proposes the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution, and utilizes the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Expand
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deepExpand
Enhanced Deep Residual Networks for Single Image Super-Resolution
This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model. Expand
Image Super-Resolution via Deep Recursive Residual Network
This paper proposes a very deep CNN model (up to 52 convolutional layers) named Deep Recursive Residual Network (DRRN) that strives for deep yet concise networks, and recursive learning is used to control the model parameters while increasing the depth. Expand