Google Tech TalksJanuary, 29 2008ABSTRACTWe present an algorithm to convert standard digital pictures into3-d models.This is a challenging problem, since an image is formed by a projection of the 3-d scene onto two dimensions, thus losing the depth information. We take a supervised learning approach to this problem, and use a Markov Random Field (MRF) to model the image depth cues as well as the relationships between different parts of the image. We show that even on unstructured scenes (of indoor and outdoor environments, including forests, trees, buildings,etc.), our algorithm is frequently able to recover fairly accurate 3-d models.We use our method to create visually pleasing 3-d flythroughs from theimage. We also present a few extensions of these ideas, such as additionally incorporating triangulation (stereo) cues, and using multiple images to produce large scale 3-d models. We also apply our methods to two robotics applications: (a) high speed offroad obstacle avoidance on an autonomously driven remote-controlled car, and (b) having a robot unload items from a dishwasher.To convert your own image of an outdoor scene, landscape, etc. to a 3-d model, please visit: http://make3d.stanford.eduJoint work with Min Sun and Andrew Y. Ng.Speaker: Ashutosh SaxenaAshutosh is a PhD candidate with Prof. Andrew Y. Ng in the ComputerScience department in Stanford University. He received his B. Tech.from Indian Institute of Technology (IIT Kanpur) in 2004.His research focuses on machine learning approaches to problems incomputer vision and in robotic manipulation. Using data-driven machinelearning techniques, he developed algorithms for creating 3-d models froma single image, and algorithms for robotic manipulation tasks such asopening doors, and grasping previously unseen objects.
Questions about Learning 3D Models from a Single Still Image
Want more info about Learning 3D Models from a Single Still Image?
Get free advice from education experts and Noodle community members.