Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines. However, they have limited expre...
Current state-of-the-art image-based scene reconstruction
techniques are capable of generating high-fidelity 3D
models when used under controlled capture conditions.
However, th...
Jean-Yves Guillemaut, Joe Kilner and Adrian Hilton
Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...
Different materials reflect light in different ways, so reflectance is a useful surface descriptor. Existing systems for measuring reflectance are cumbersome, however, and although...
We propose a method that computes a conformal mapping from a multiply connected mesh to the so-called slit domain, which consists of a canonical rectangle or disk in which 3D curve...
Yalin Wang, Xianfeng Gu, Tony F. Chan, Paul M. ...