Learning from irregularly sampled data for endomicroscopy super-resolution: a comparative study of sparse and dense approaches

Keyphrases

• Super-resolution 100%
• Irregularly Sampled Data 100%
• Probe-based Confocal Laser Endomicroscopy (pCLE) 100%
• Endomicroscopy 100%
• Convolutional Neural Network 40%
• Trainable 20%
• Kernel Regression 20%
• Deep Learning Architectures 10%
• Reconstruction Method 10%
• Structural Similarity Index 10%
• Cartesian Grid 10%
• Linear Interpolation 10%
• Current Probe 10%
• Dense Convolutional Neural Network 10%
• Image Quality 10%
• Image Quality Assessment 10%
• Irregular Data 10%
• Network Layer 10%
• Image Reconstruction 10%
• Sparse Convolutional Neural Network 10%
• Peak Signal to Noise Ratio 10%
• Synthetic Data 10%
• Optical Biopsy 10%
• Super-resolution Algorithm 10%
• Optical Fiber 10%
• Neural Network Framework 10%

Engineering

• Convolutional Neural Network 100%
• Sampled Data 100%
• Current Probe 20%
• Deep Learning Method 20%
• Structural Similarity 20%
• Fiber Optics 20%
• Peak Signal 20%
• Metrics 20%
• Image Reconstruction 20%
• Similarity Index 20%
• Linear Interpolation 20%
• Cartesian Grid 20%
• Input Data 20%
• Signal-to-Noise Ratio 20%
• Image Quality Assessment 20%

Computer Science

• super resolution 100%
• Convolutional Neural Network 100%
• Deep Learning Method 20%
• Generate Signal 20%
• Resolution Method 20%
• Structural Similarity 20%
• Network Layer 20%
• Image Reconstruction 20%
• Linear Interpolation 20%
• Synthetic Data 20%
• Image Quality 20%
• peak signal to noise ratio 20%
• Image Quality Assessment 20%