@article {Alhaija2018, title = {Augmented Reality Meets Computer Vision}, journal = {International Journal of Computer Vision}, volume = {In press}, year = {2018}, pages = {1{\textendash}13}, abstract = {The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation and object detection models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment real images with virtual objects. This allows us to create realistic composite images which exhibit both realistic background appearance and a large number of complex object arrangements. In contrast to modeling complete 3D environments, our augmentation approach requires only a few user interactions in combination with 3D shapes of the target object. Through extensive experimentation, we conclude the right set of parameters to produce augmented data which can maximally enhance the performance of instance segmentation models. Further, we demonstrate the utility of our approach on training standard deep models for semantic instance segmentation and object detection of cars in outdoor driving scenes. We test the models trained on our augmented data on the KITTI 2015 dataset, which we have annotated with pixel-accurate ground truth, and on Cityscapes dataset. Our experiments demonstrate that models trained on augmented imagery generalize better than those trained on synthetic data or models trained on limited amount of annotated real data.}, keywords = {autonomous driving, data augmenta-, instance segmentation, synthetic training data, tion}, author = {Hassan Abu Alhaija and Mustikovela, Siva Karthik and Mescheder, Lars and Geiger, Andreas and Carsten Rother} }