In deep learning and computer vision, data is often assumed to lie on a low-dimensional manifold, embedded within the potentially high-dimensional input space — as, for example, for images. However, the manifold is usually not known which hinders deeper understanding of many phenomena in deep learning, such as adversarial examples. Based on my recent CVPR’19 paper, I want to present FONTS, a MNIST-like, synthetically created dataset with known manifold to study adversarial example.
Obtaining high-quality visualizations of 3D data such as triangular meshes or occupancy grids, as needed for publications in computer graphics and computer vision, is difficult. In this article, I want to present a GitHub repository containing some utility scripts for paper-ready visualizations of meshes and occupancy grids using Blender and Python.
Triangular meshes are commonly used to represent various shapes in computer graphics and computer vision. However, for various deep learning techniques, triangular meshes are not well suited. Therefore, meshes are commonly voxelized into occupancy grids or signed distance functions. This article presents a C++ tool allowing efficient voxelization of (watertight) meshes.
Automatically obtaining high-quality watertight meshes in order to derive well-defined occupancy grids or signed distance functions is a common problem in 3D vision. In this article, I present a mesh fusion approach for obtaining watertight meshes. In combination with a standard mesh simplification algorithm, this approach produces high-quality, but lightweight, watertight meshes.
We are releasing the code and data corresponding to our ArXiv pre-print on weakly-supervised 3D shape completion — a follow-up work on our earlier CVPR’18 paper. The article provides links to the GitHub repositories and data downloads as well as detailed descriptions. It also highlights the differences between the two papers.
Learning 3D shape completion under weak supervision; on ShapeNet, ModelNet, KITTI and Kinect data; published at CVPR and on ArXiv.
Finally, we are able to release the code and the data corresponding to our CVPR’18 paper on “Learning 3D Shape Completion from Laser Scan Data with Weak Supervision”. In this article, I want to briefly outline the released code and data.
As part of the online course Creative Applications of Deep Learning with TensorFlow, and to get started with TensorFlow, I implemented some experiments on MNIST. Specifically, I tested different architectures, activation functions and initialization schemes. While these experiments are not systematic enough for reliable results, they can be useful as an introduction to TensorFlow. In this article, I want to share the code and the corresponding presentation.
Weakly-supervised shape completion of cars on KITTI using variational auto-encoders; including two synthetic ShapeNet-based benchmark datasets.
This article discusses how to visualize triangular meshes available in Object File Format (.off) in Python using occmodel. Installation instructions for installing occmodel on Ubuntu are included.