We present a novel method for globally optimal surface segmentation of multiple mutually interacting objects, incorporating both edge and shape knowledge in a 3-D graph-theoretic a...
Qi Song, Xiaodong Wu, Yunlong Liu, Mark Smith, Joh...
The suitability of polar representation for quantitative image processing tasks is investigated. The classical colour polar-based representations (HLS, HSV, etc.) lead to brightne...
This paper presents a purely image-based approach to fusing foreground silhouette information from multiple arbitrary views. Our approach does not require 3D constructs like camer...
We present a method to generate stylized stereo imagery that effectively communicates shape and distance of the depicted scene objects. We use computer vision techniques to analyz...
Efstathios Stavrakis, Michael Bleyer, Danijela Mar...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...