supported by National Natural Science Foundation of China (Nos. 61402300, 61373160, 61363048, 61173102, 61370143, and 61202261);Natural Science Foundation of Hebei Province (No. F2014210127);the Funded Projects for Introduction of Overseas Scholars of Hebei Province;Funds for Excellent Young Scholar of Shijiazhuang Tiedao University;Scientific and Technological Development Plan of Jilin Province (No. 20130522113JH)
In this paper, we propose least-squares images(LS-images) as a basis for a novel edgepreserving image smoothing method. The LS-image requires the value of each pixel to be a convex linear combination of its neighbors,...
Supported by National Natural Science Foundation of China(Nos.11472073,61173102 and 61370143)
We introduce an almost-automatic technique for generating 3D car styling surface models based on a single side-view image. Our approach combines the prior knowledge of car styling and deformable curve network model to...
Supported by National Natural Science Foundation of China(Nos.61402300,61373160,61363048,61173102,61370143);Natural Science Foundation of Hebei Province(F2014210127);Funded Projects for Introduction of Overseas Scholars of Hebei Province
In this paper, we propose anovel geometricaldetail editing method for triangulatedmeshmodels based on filtering robust differential edge coordinates.Theintroduceddetail editing consists ofnot only feature-preserving d...
Partially Supported by National Natural Science Foundation of China(No.61173102)
Motion deblurring is a basic problem in the field of image processing and analysis. This paper proposes a new method of single image blind deblurring which can be significant to kernel estimation and non-blind deconvo...