UC San Diego
Priors and learning based methods for super-resolution
- Author(s): Kumar, Sanjeev
- et al.
In this dissertation we propose priors and learning based methods for super-resolution and other video processing applications. We also propose efficient algorithms for global motion estimation. We propose total subset variation (TSV), a convexity preserving generalization of total variation (TV) prior, for higher order clique MRF. A proposed differentiable approximation of the TSV prior makes it amenable for use in large images (e.g. 1080p). A generalization to vector valued data enables use of the TSV prior for color images and motion field. A convex relaxation of sub-exponential distribution is proposed as a criterion to determine parameters of the optimization problem resulting from the TSV prior. For super-resolution application, experiments show reconstruction error improvement in terms of PSNR as well as Structural Similarity (SSIM) with respect to TV and other methods. We also propose an image up-scaling algorithm based on ν support vector regression. Working in the pixel domain, spatial neighborhood in the form of rectangular patches are used to determine the high resolution pixels at the center of the patch. Since, interpolation involves matching the test patch against a descriptive subset of training patches (support vectors) to find similar training patches which then have higher influence on the result of interpolation, the approach is inherently adaptive to local image content. We also investigate [nu] support vector regression for compression artifact reduction application. For global motion estimation application, we propose a fast and robust 2D affine global motion estimation algorithm based on phase-correlation in Fourier-Mellin domain and robust least square model fitting of sparse motion vector field. Rotation-scale- translation (RST) approximation of affine parameters is obtained at coarsest level of image pyramid, as opposed to only initial translation estimate, thus ensuring convergence for much larger range of motions. Despite working at coarsest resolution level, use of subpixel- accurate phase correlation provides sufficiently accurate coarse estimates for subsequent refinement stage of the algorithm. Refinement stage consists of RANSAC based robust least-square model fitting to sparse motion vector field, estimated using block-based subpixel-accurate phase correlation at randomly selected high activity regions in finest level of image pyramid. Resulting algorithm is very robust to outliers like foreground objects and flat regions. Experimental results show proposed algorithm is capable of estimating larger range of motions as compared to MPEG-4 verification model, while achieving a speed-up of 200. A combination of priors for statistics of single frames of natural video and motion estimation between different frames of video is essential for good performance of any general video processing application