Self-tuned deep super resolution

Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on external examples with proper data augmentations. It is then fine-tuned with multi-scale self examples from each input, where the reliability of self examples is explicitly taken into account. We also enhance the model performance by sub-model training and selection. The DJSR model is extensively evaluated and compared with state-of-the-arts, and show noticeable performance improvements both quantitatively and perceptually on a wide range of images.

• Publication year

  2015

• Venue

  2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

• Publication date

  2015-04-21

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CVPRW.2015.7301266arXiv 1504.05632
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Jointly Optimized Regressors for Image Super‐resolution

  2015cited by this paper
• Designing a composite dictionary adaptively from joint examples

  2015cited by this paper
• Learning Super-Resolution Jointly From External and Internal Examples

  2015cited by this paper
• Deep Network Cascade for Image Super-resolution

  2014cited by this paper
• A joint perspective towards image super-resolution: Unifying external- and self-examples

  2014cited by this paper
• Learning a Deep Convolutional Network for Image Super-Resolution

  2014cited by this paper
• Robust Classification Under Sample Selection Bias

  2014cited by this paper
• An Analysis of Unsupervised Pre-training in Light of Recent Advances

  2014cited by this paper
• A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution

  2014cited by this paper
• Zero-bias autoencoders and the benefits of co-adapting features

  2014cited by this paper
• Fast Image Super-Resolution Based on In-Place Example Regression

  2013cited by this paper
• Learning How to Combine Internal and External Denoising Methods

  2013cited by this paper
• Combining the power of Internal and External denoising

  2013cited by this paper
• Image Denoising and Inpainting with Deep Neural Networks

  2012cited by this paper
• Coupled Dictionary Training for Image Super-Resolution

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

  2011cited by this paper
• Image and video upscaling from local self-examples

  2011cited by this paper
• Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach

  2011cited by this paper
• Adaptive deconvolutional networks for mid and high level feature learning

  2011cited by this paper
• Internal statistics of a single natural image

  2011cited by this paper
• Exploiting Self-similarities for Single Frame Super-Resolution

  2010cited by this paper
• Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion

  2010cited by this paper
• Image Super-Resolution Via Sparse Representation

  2010cited by this paper
• Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

  2010cited by this paper
• Super-resolution from a single image

  2009cited by this paper
• Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries

  2006cited by this paper
• Image quality assessment: from error visibility to structural similarity

  2004cited by this paper

• Revealing the Dark Side of Non-Local Attention in Single Image Super-Resolution

  2024cites this paper
• Image super resolution boosting using beta wavelet

  2023cites this paper
• Deep recurrent residual channel attention network for single image super-resolution

  2023cites this paper
• Single Image Super-Resolution Methods: A Survey

  2022cites this paper
• Wavelet-based super resolution using pansharpened multispectral images

  2021cites this paper
• DEEP LEARNING APPLICATION FOR IMAGE ENHANCEMENT

  2021cites this paper
• Accurate Magnetic Resonance Image Super-Resolution Using Deep Networks and Gaussian Filtering in the Stationary Wavelet Domain

  2021cites this paper
• Single image super-resolution reconstruction based on fusion of internal and external features

  2021cites this paper
• Deep learning for high-resolution and high-sensitivity interferometric phase contrast imaging

  2020cites this paper
• Internal Learning for Image Super-Resolution by Adaptive Feature Transform

  2020influential citation
• Kernel Based Progressive Distillation for Adder Neural Networks

  2020cites this paper
• Receptive Field Size Versus Model Depth for Single Image Super-Resolution

  2020cites this paper
• Image super-resolution reconstruction based on generative adversarial network model with double discriminators

  2020cites this paper
• Self-Supervised Fine-tuning for Image Enhancement of Super-Resolution Deep Neural Networks

  2019cites this paper
• Enhanced two-phase residual network for single image super-resolution

  2019cites this paper
• Single Image Super-Resolution: From Sparse Coding to Deep Learning

  2019cites this paper
• Single image super-resolution reconstruction using multiple dictionaries and improved iterative back-projection

  2019cites this paper
• Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study

  2019cites this paper
• Multipath feedforward network for single image super-resolution

  2019cites this paper
• An adaptive anchored neighborhood regression method for medical image enhancement

  2019cites this paper
• Image Super Resolution Using Fractal Coding and Residual Network

  2019cites this paper
• Adaptive Transform Domain Image Super-Resolution via Orthogonally Regularized Deep Networks

  2019cites this paper
• UG 2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments

  2019cites this paper
• Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks.

  2019cites this paper
• Feature Extraction from Electronic Health Records of Diabetic Nephropathy Patients with Convolutioinal Autoencoder

  2018cites this paper
• Recent Advances in Deep Learning for Single Image Super-Resolution

  2018cites this paper
• Enhancing Digital Zoom in Mobile Phone Cameras by Low Complexity Super-Resolution

  2018cites this paper
• Video Super Resolution with Generative Adversarial Network

  2018cites this paper
• Advanced Super-Resolution Using Lossless Pooling Convolutional Networks

  2018cites this paper
• Super-Resolution via Image-Adapted Denoising CNNs: Incorporating External and Internal Learning

  2018cites this paper
• Global motion based video super-resolution reconstruction using discrete wavelet transform

  2018cites this paper
• Image Super-Resolution via Dual-State Recurrent Networks

  2018cites this paper
• Deep Image Super Resolution via Natural Image Priors

  2018cites this paper
• Orthogonally Regularized Deep Networks for Image Super-Resolution

  2018cites this paper
• Residual Learning Dehazing Net

  2018cites this paper
• Single Image Super-Resolution via Adaptive Transform-Based Nonlocal Self-Similarity Modeling and Learning-Based Gradient Regularization

  2017cites this paper
• Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders

  2017cites this paper
• Robust emotion recognition from low quality and low bit rate video: A deep learning approach

  2017cites this paper
• Computed tomography super-resolution using convolutional neural networks

  2017cites this paper
• A Noise-Resilient Super-Resolution Framework to Boost OCR Performance

  2017cites this paper
• Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons

  2017cites this paper
• An All-in-One Network for Dehazing and Beyond

  2017cites this paper
• Volumetric Super-Resolution of Multispectral Data

  2017cites this paper
• Deep learning based frameworks for image super-resolution and noise-resilient super-resolution

  2017cites this paper
• Super-Resolution via Deep Learning

  2017cites this paper
• Image Super-Resolution via Deep Recursive Residual Network

  2017cites this paper
• Deep CNN-Based Super-Resolution Using External and Internal Examples

  2017influential citation
• Deep Wavelet Prediction for Image Super-Resolution

  2017cites this paper
• AOD-Net: All-in-One Dehazing Network

  2017cites this paper
• Color-based and Rotation Invariant Self-similarities

  2017cites this paper
• Face Hallucination with Tiny Unaligned Images by Transformative Discriminative Neural Networks

  2017cites this paper
• Enhanced Signal Recovery via Sparsity Inducing Image Priors

  2017cites this paper
• Single image super-resolution using a deep encoder-decoder symmetrical network with iterative back projection

  2017cites this paper
• Multi-frame Super Resolution Reconstruction Based on Bayesian Inference

  2017cites this paper
• Single image super-resolution based on neural networks for text and face recognition

  2017cites this paper
• Deep learning-inspired image quality enhancement

  2017cites this paper
• Learning and Mapping onto Manifolds with Applications to Patch-based Image Processing

  2016cites this paper
• Zhangyang ( Atlas ) Wang 1 Research Overview

  2016cites this paper
• Super Resolution based on Deep Learning Technique for constructing Digital Elevation Model

  2016cites this paper
• Super-resolution of compressed videos using convolutional neural networks

  2016cites this paper
• Deep learning based image super-resolution with coupled backpropagation

  2016influential citation
• Global-Local Face Upsampling Network

  2016cites this paper
• Learning a multiscale patch-based representation for image denoising in X-RAY fluoroscopy

  2016cites this paper
• Studying Very Low Resolution Recognition Using Deep Networks

  2016cites this paper
• Video Super-Resolution With Convolutional Neural Networks

  2016cites this paper
• Realizing Real-Time Deep Learning-Based Super-Resolution Applications on Integrated GPUs

  2016cites this paper
• Robust Single Image Super-Resolution via Deep Networks With Sparse Prior

  2016cites this paper
• Blind Super-Resolution with Deep Convolutional Neural Networks

  2016cites this paper
• D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images

  2016cites this paper
• Learning Super-Resolution Jointly From External and Internal Examples

  2015cites this paper
• Designing a composite dictionary adaptively from joint examples

  2015cites this paper