All Projects

Doctoral Thesis, University of Amsterdam

We collect from open sources a large-scale dataset of ALS point clouds and corresponding DTMs. The baseline method extracts DTMs directly from ALS point clouds via rasterization techniques, coined DeepTerRa.

To facilitate machine learning for agricultural purposes which involve with unstructured natural scenes we introduce a synthetic dataset of Enclosed garDEN scenes, or EDEN.

We predict depth from monocular image and construct partial point clouds to capture the geometry of the object, which can be freely rotated to the desired viewpoint and projected into a new image....

We study the influence between the three modalities: how one impacts on the others and their efficiency in combination using convolutional refine network

Simple Android game project for the course of Mobile Aplications and Services, Fall 2014, at EURECOM institute, Campus SophiaTech, France.

Short and fun video clip course on 3D and Virtual Imaging, Spring 2014, at EURECOM institute, Campus SophiaTech, France.