Texture Image Extrapolation for Compression Sung-Won Yoon & SeongTaek Chung Stanford University December 4, 2000
Outline Motivation : Recover the whole image using partial information of the image Methods : non-parametric sampling estimation using subband decomposition of wavelet coefficients estimation by induced correlation
Non-parametric Sampling Based on the approach of Alexei A. Efros and Thomas K. Leung Method
Results Big Hole Scattered Holes Window size Filling order Better performance More data needed
Estimation Using Subband Decomposition Spatial locality Similarity between subbands Estimate A from B by use of the mapping from C to B
Model One-to-four linear mapping A. Pentland & B. Horowitz Mapping between pairs of subbands are similar Full search possible because repetitiveness of texture image
Results Original Detail level 1 zeroed Detail level 1 estimated
Limitations Statistical differences in different subbands Assumption of propagation of mapping does not hold in general Very limited mapping information from lower subbands
Estimation by Induced Correlation System Model
Results Original Estimated image 1 (PSNR: 15.33dB) Interpolated image (PSNR : 12.73dB)
Conclusions Non-parametric sampling window size and computation load Estimation using subband decomposition lack of mapping similarity between pairs of subbands different statistical characteristics for different subbands Estimation by induced correlation optimal filter is hard to find