260 likes | 529 Views
Fast Direct Super-Resolution by Simple Functions. Chih -Yuan Yang and Ming- Hsuan Yang 12/14/13. Outline. Introduction Related work Proposed method Experimental results Conclusions. Introduction. Super-Resolution = Predicting pixel intensities From single or multiple image(s)
E N D
Fast Direct Super-Resolution by Simple Functions Chih-Yuan Yang and Ming-Hsuan Yang 12/14/13
Outline • Introduction • Related work • Proposed method • Experimental results • Conclusions
Introduction • Super-Resolution = Predicting pixel intensities • From single or multiple image(s) • For spatial or temporal intestines 480 120 320 80
Challenges • Effectiveness • Numerous pixel intensities • Stability • Various image content • Computational load
Related Work - Bicubic Interpolation • Predicting intensities by interpolating nearbypixels • Simple and fast • But over-smooth
Self-Similar Exemplars [Glasner 11] I4 • Predict HR patches through example patches found in a self-generated image pyramid • Sharp and clear edges • Blurred textures • Slow I3 I2 I1 I0 I-1 I-2 I-3
Gradient Profile Prior [Sun08] • Predict intensities by a edge model • Sharp edges, but jaggy • Only effective for edges
Sparse Representation [Yang08] • Predicting HR patch features by learned sparse dictionaries • Rich details • Noise artifacts along edges
Proposed Method • Split LR feature space for effectiveness • Use simple features and simple functions for speed • Exploit a large image set to collect training samples • Asymmetric computational load • slow for training • fast for test
Training Phase (1)Generate LR images • Generate LR images from HR training images • Extract patch pairs in LR and HR • Since there is a convolution for HR images, we cropLR patches affected by predicted HR pixels (blue region)
Training Phase (2)Extract LR/HR features • Features: • LR: LR intensity minus the mean of the LR patches • HR: HR intensity minus the mean of the LR patches • High-frequency information • Cluster the LR training features by K-mean • split the LR feature space into K subspaces
Training Phase (3)Collect training instances • Randomly select sufficeint LR/HR feature pairs for each cluster • For some cluster centers, use bicubic interpolation if no sufficient instances available
Training Phase (4)Learn regression coefficients • C: coefficients • W: HR features (1000 instances) • V: LR features (1000 instances)
Test Phase • Crop LR patches • Compute patch mean, and extract LR features • Find the closest cluster center • Compute HR features • HR patch intensity = HR feature + LR patch mean • Average overlapped HR patches as output
Experimental Results - IC • No groundtruth image
Performance (averaged) and Execution Time for BSD200 Dataset
Conclusions • Clear and sharp edges • Rich texture details • Easy for implementation • Fast to generate SR images
Insight • Split of the LR feature space • K has to be large enough • Exploit a large image set to collect sufficient examples for high-frequency patches • Regression methods make little difference
Code and Dataset Available • https://eng.ucmerced.edu/people/cyang35 • Including code for training phase