We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
Gabriel J. Brostow, Jamie Shotton, Julien Fauqueur...
Recognition of specular objects is particularly difficult because their appearance is much more sensitive to lighting changes than that of Lambertian objects. We consider an appr...
Occlusion is a significant challenge for many tracking algorithms. Most current methods can track through transient occlusion, but cannot handle significant extended occlusion whe...
Neel Joshi, Shai Avidan, Wojciech Matusik, David J...
We propose a new free-view video system that generates immersive 3D video from arbitrary point of view, using outer cameras and an inner omni-directional camera. The system recons...
Hansung Kim, Itaru Kitahara, Ryuuki Sakamoto, Kiyo...
We propose a novel approach for shape-based segmentation based on a specially designed level set function format. This format permits us to better control the process of object re...