3 papers
cs.CV2020
AutoSimulate: (Quickly) Learning Synthetic Data Generation
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal +2
Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with t…
cs.CV2019
Photorealistic Image Synthesis for Object Instance Detection
Tomas Hodan, Vibhav Vineet, Ran Gal +6
We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images…
cs.CV2015
ASIST: Automatic Semantically Invariant Scene Transformation
Or Litany, Tal Remez, Daniel Freedman +3
We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in…