My work “Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video” was shortlisted among the best paper finalists at the Conference on Computer Vision and Pattern Recognition 2019 (CVPR 2019) that took place in Long Beach (CA, USA) in summer.

The paper introduces a new approach for automatic reconstruction of 3D motion and actuation forces of a person interacting with an object from a single RGB video. The objective is to enable robots to learn how to manipulate tools by watching instructional videos that are available at, for example, Youtube. The approach was developed in collaboration with researchers from LAAS-CNRS in Toulouse.

The project Webpage is available online.

To run a Docker container to support a development workflow, we will do the following:

• Mount our source code into the container
• Install all dependencies, including the “dev” dependencies
• Start nodemon to watch for filesystem changes

Cette page est un (non exhaustive & usage personnel) aide-mémoire sur les raccourcis de GNU Emacs. Mais ce serait super si cela pouvait aider quelqu’un d’autre.

The following Python function converts a 3 x nf matrix, axisAngles, whose columns are axis-angles, to a 4 x nf matrix of quaternions under the (x,y,z,w) convention. Note that the quaternions should always have norm 1.

I joined the Gepetto team of LAAS-CNRS, Toulouse, France, as a visiting student this winter. I had a great time with the robotics researchers at LAAS, during which I gave a public talk to present my work. By the way, Toulouse was truly a beautiful city.