Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets

اسناد مشابه

• Single Satellite Imagery Super-Resolution Based on Hybrid Non-local Similarity Constrained Convolution Sparse Coding

  مقاله‌ی دسترسی آزاد۲۰۲۱IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingNanChen, LichunSui, BiaoZhang, HongjieHe

• Compressed Sensing Dynamic MRI Reconstruction Using GPU-accelerated 3D Convolutional Sparse Coding

  سند علمی۲۰۱۶MICCAITran Minh Quan, Won-Ki Jeong

  In this paper, we introduce a fast alternating method for reconstructing highly undersampled dynamic MRI data using 3D convolutional sparse coding. The proposed solution leverages Fourier Convolution Theorem to accelerate the process of learning a set of 3D filters and iterativel

• Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decomposition

  سند علمی۲۰۱۴Computer Vision and Image UnderstandingChunjie Zhang, Jing Liu, Chao Liang, Zhe Xue

  We propose an image classification framework by leveraging the non-negative sparse coding, correlation constrained low rank and sparse matrix decomposition technique (CCLR-ScSPM). First, we propose a new non-negative sparse coding along with max pooling and spatial pyramid matchi

• Convolutional Sparse Coding for High Dynamic Range Imaging

  سند علمی۲۰۱۶Comput. Graph. ForumAna Serrano, Felix Heide, Diego Gutierrez, Gordon Wetzstein

  Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image with spatially-varying

• Convolutional Sparse Coding-based Image Decomposition

  سند علمی۲۰۱۶BMVCHe Zhang, Vishal M. Patel

  We propose a novel sparsity-based method for cartoon and texture decomposition based on Convolutional Sparse Coding (CSC). Our method first learns a set of generic filters that can sparsely represent cartoon and texture type images. Then using these learned filters, we propose a

• Image Super-Resolution with Fast Approximate Convolutional Sparse Coding

  سند علمی۲۰۱۴ICONIPChristian Osendorfer, Hubert Soyer, Patrick van der Smagt

  We present a computationally e cient architecture for image super-resolution that achieves state-of-the-art results on images with large spatial extend. Apart from utilizing Convolutional Neural Networks, our approach leverages recent advances in fast approximate inference for sp