We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
This paper presents a complete solution to estimating a scene’s 3D geometry and appearance from multiple 2D images by using a statistical inverse ray tracing method. Instead of ...
Images of cellular structures in growing plant roots acquired using confocal laser scanning microscopy (CLSM) have some unusual properties that make motion estimation challenging....
Timothy J. Roberts, Stephen J. McKenna, Cheng-Jin ...
The concept of the Bayesian optimal single threshold is a well established and widely used classification technique. In this paper, we prove that when spatial cohesion is assumed ...
High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...