Abstract. We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) ...
Since it is hard to handcraft the prior knowledge in a shape detection framework, machine learning methods are preferred to exploit the expert annotation of the target shape in a d...
Yefeng Zheng, Xiang Sean Zhou, Bogdan Georgescu, S...
Band ratios have many useful applications in hyperspectral image analysis. While optimal ratios have been chosen empirically in previous research, we propose a principled algorith...
Antonio Robles-Kelly, Nianjun Liu, Terry Caelli, Z...
This paper examines high dimensional regression with noise-contaminated input and output data. Goals of such learning problems include optimal prediction with noiseless query poin...
Abstract. In this this paper, we present a solution to the simultaneous localization and mapping (SLAM) problem for a robot equipped with a single perspective camera. We track extr...