UCSD 博士论文 Priors and Learning Based Methods for Super-Resolution - 源码 - 源码 - 免费下载

UCSD 博士论文 Priors and Learning Based Methods for Super-Resolution

文件大小： 3479k

源码售价： 10 个金币积分规则积分充值

资源说明：In this dissertation we propose priors and learning based methods for super- resolution and other video processing applications. We also propose eﬃcient al- gorithms for global motion estimation and projection on L1 ball under box con- straints. We propose total subset variation (TSV), a convexity preserving general- ization 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 optimiza- tion problem resulting from the TSV prior. For super-resolution application, ex- periments 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 rect- angular patches are used to determine the high resolution pixels at the center of the patch. Since, interpolation involves matching the test patch against a descrip- tive 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 ν support vector xiiiregression 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 [2] [3], thus ensuring convergence for much larger range of motions. Despite working at coarsest resolution level, use of subpixel-accurate phase correlation [4] provides suﬃciently accurate coarse estimates for subsequent reﬁnement stage of the algo- rithm. Reﬁnement stage consists of RANSAC [5] 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 esti- mating 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 perfor- mance of any general video processing application.

部分文件列表（点击文件名可查看文件内容）

					
									本源码包内暂不包含可直接显示的源代码文件，请下载源码包。