• [November 2017] Check out our work on deep sensor fusion for 3D object detection on Arxiv.
  • [August 2017] Our short paper on Neural Task Programming has been accepted at CoRL 2017. Full paper (in submission) has been released on Arxiv.
  • [April 2017] Check out the code release of our CVPR 2017 submission!

Selected Publications

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image. We propose a novel end-to-end model that generates such structured scene representation from an input image.
In CVPR 2017

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The network learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data using 3D-Convolutional LSTM which allows attention mechanism to focus on visible parts in 3D. Our network takes in one or more images of an object instance from arbitrary viewpoints and outputs a reconstruction of the object in the form of a 3D occupancy grid.
In ECCV 2016

Publication List


Coming Soon