Learn More
3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-theart methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view(More)
1. Details on Model Training Training for Our Volumetric CNNs To produce occupancy grids from meshes, the faces of a mesh are subdivided until the length of the longest edge is within a single voxel; then all voxels that intersect with a face are marked as occupied. For 3D resolution 10,30 and 60 we generate voxelizations with central regions 10, 24, 54 and(More)
In this report, we proposed a 3D reconstruction method for the full-view fisheye camera. The camera we used is Ri-coh Theta, Fig. 1, which captures spherical images and has a wide field of view (FOV). The conventional stereo appo-rach based on perspective camera model cannot be directly applied and instead we used a spherical camera model to depict the(More)
Stanford Center for Professional Development (SCPD) has developed a great database of engineering courses' lecture videos. These videos are very useful for students both on and off campus. Yet in this database it is hard to locate the time stamp where professor was talking about a particular concept, equation, graph, etc. This feature would be very helpful(More)
  • 1