In this work we deal with the problem of modelling and exploiting the interaction between the processes of image segmentation and object categorization. We propose a novel framewo...
We propose a novel framework to build descriptors of local intensity that are invariant to general deformations. In this framework, an image is embedded as a 2D surface in 3D spac...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
We introduce an iterative algorithm for shape reconstruction from multiple images of a moving (Lambertian) object illuminated by distant (and possibly time varying) lighting. Star...
Jongwoo Lim, Jeffrey Ho, Ming-Hsuan Yang, David J....
Many parameter estimation problems admit divide and conquer or partitioning techniques in order to reduce a highdimensional task into several reduced-dimension problems. These tec...
Color appearance of an object is significantly influenced by the color of the illumination. When the illumination color changes, the color appearance of the object will change acc...
We introduce a framework for computing statistically optimal estimates of geometric reconstruction problems. While traditional algorithms often suffer from either local minima or ...
Visual codebook based quantization of robust appearance descriptors extracted from local image patches is an effective means of capturing image statistics for texture analysis and...
Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally lin...
The geometry of plane-based calibration methods is well understood, but some user interaction is often needed in practice for feature detection. This paper presents a fully automa...