NVIDIA Research at ICCV: Meta-Sim: Learning to Generate Synthetic Datasets

Originally published at: https://developer.nvidia.com/blog/nvidia-at-iccv-meta-sim-learning-to-generate-synthetic-datasets/

At the International Conference on Computer Vision in Seoul, Korea, NVIDIA researchers, in collaboration with University of Toronto, the Vector Institute and MIT presented Meta-Sim, a deep learning model that can generate synthetic datasets with unlabeled real data (i.e. camera footage), bridging the gap between real and synthetic training data. Meta-Sim is a method to…

Very Interesting

Thanks! Have you seen the Meta-Sim 2 paper yet?