VASC Seminar
Robotic Grasping and Depth Perception: Learning 3D Models from a Single Image
Event Location: NSH 1507 Abstract: Learning algorithms to predict depth and infer 3-d models, given just a single still image. Applications included creating immersive 3-d experience from users' photos, improving performance of stereovision, creating large-scale models from a few images, robot navigation, etc. Learning algorithms to predict robotic grasps, even for objects of types never [...]
Perception on an Offroad Robot: Shallow and Deep Learning Architectures
Event Location: 1507 NSHBio: I am a second year Robograd (PhD student at the Robotics Institute, Carnegie Mellon University). My research focus is to make pretty pictures (Computer Graphics) and to make sense out of ugly pictures (Computer Vision). More technically, I am interested in understanding how light interacts with media like smoke,dust, fog, ocean [...]