In this paper we explore the problem of accurately segmenting a person from a video given only approximate location of that person. Unlike previous work which assumes that the app...
Antialiasing of ray traced images is typically performed by supersampling the image plane. While this type of filtering works well for many algorithms, it is much more efficient t...
A new approach to computing a panoramic (360 degrees) depth map is presented in this paper. Our approach uses a large collection of images taken by a camera whose motion has been c...
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...