AutoSimulate: (Quickly) Learning Synthetic Data Generation

no code implementations • ECCV 2020 • Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal, Philip H. S. Torr, Vibhav Vineet

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems.

Synthetic Data Generation

Photorealistic Image Synthesis for Object Instance Detection

no code implementations • 9 Feb 2019 • Tomas Hodan, Vibhav Vineet, Ran Gal, Emanuel Shalev, Jon Hanzelka, Treb Connell, Pedro Urbina, Sudipta N. Sinha, Brian Guenter

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.

6D Pose Estimation 6D Pose Estimation using RGB +3

ASIST: Automatic Semantically Invariant Scene Transformation

no code implementations • 4 Dec 2015 • Or Litany, Tal Remez, Daniel Freedman, Lior Shapira, Alex Bronstein, Ran Gal

We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts.

Object