Recently, methods for estimating 3D scene geometry or absolute scene depth information from 2D image content have been proposed. However, general applicability of these methods in...
We present a method for the simultaneous detection and segmentation of objects from static images. We employ lowlevel contour features that enable us to learn the coarse object sh...
Abstract. Rigidity and reflectance are key object properties, important in their own rights, and they are key properties that stratify motion reconstruction algorithms. However, th...
We present a region-based active contour detection algorithm
for objects that exhibit relatively homogeneous photometric
characteristics (e.g. smooth color or gray levels),
embe...
Ganesh Sundaramoorthi, Stefano Soatto, Anthony Yez...
The Conditional Random Fields (CRF) model, using
patch-based classification bound with context information,
has recently been widely adopted for image segmentation/
labeling. In...