← Search

John McCormac

2 accepted papers

2017

SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?

ICCV 2017poster

We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection. It also provides perfect camera poses and depth data, allowing investigation into geometric computer vision problem…

Cited by 362PDFcodeScholar
2017

SemanticFusion: Dense 3D semantic mapping with convolutional neural networks

ICRA 2017poster

Ever more robust, accurate and detailed mapping using visual sensing has proven to be an enabling factor for mobile robots across a wide variety of applications. For the next level of robot intelligence and intuitive user interaction, maps need to extend beyond geometry and appearance - they need to…

Cited by 830SourceScholar