2D and 3D object detection by exploiting segmentation and contextual information

Object detection is one of the main challenges of computer vision. In the standard setting, we are given an image and the goal is to place bounding boxes around the objects and recognize their classes. In robotics, estimating additional information such as accurate viewpoint or detailed segmentation is important for planning and interaction. In this talk, I'll approach detection in three scenarios: purely 2D, 3D from 2D and 3D from 3D and show how different types of information can be used to significantly boost the current state-of-the-art in detection.