We propose a new method to solve a problem of image restoration with many different aspects: reconstruction from irregular samples, deconvolution and denoising. The model we propo...
A surface reconstruction technique based on minimization of the total variation of the gradient is introduced. Convergence of the method is established, and an interior-point algor...
The appearance manifold [WTL 06] is an efficient approach for modeling and editing time-variant appearance of materials from the BRDF data captured at single time instance. Howeve...
Su Xue, Jiaping Wang, Xin Tong, Qionghai Dai, Bain...
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task ...
We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to hand...