I1.4: Invited Paper: Indoor Scene Understanding from RGB-D Images

Our goal is to be able to align objects in an RGB-D image with 3D models from a library. Our pipeline for this task involves detecting and segmenting objects and estimating coarse pose using a convolutional neural network, followed by inserting the rendered model in the scene.

[1]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.