Vincent Casser


I am a machine learning researcher and software engineer with major interests in visual computing. My previous research was mostly related to computer vision: in domains such as computational perception, autonomous navigation and biomedical imaging. I have high interests in interdisciplinary applications, with my previous projects relating to the study of human memory (with MIT), applications in healthcare (with Massachusetts General Hospital), astronomy (with Harvard-Smithsonian Center for Astrophysics) and microscopy (with Harvard Lichtman Lab). I’ve been an avid programmer for many years now, with extensive experience in a variety of technologies and languages. Several years ago, I also taught several programming courses in college as a teaching fellow. Before doing computer science research, I developed various software applications for non-scientific purposes.

I hold a Master’s degree in Computational Science and Engineering from Harvard University. I spent my year of research in Aude Oliva’s lab at MIT CSAIL, where I computationally modeled human visual memory as part of the Memento project. During my time at Harvard, I also interned in the Google Brain Robotics team under Anelia Angelova. Previously, I earned a BSc in Computer Science from the University of Bonn, Germany in 2016, where I minored in physics and astronomy, and worked as a research intern at King Abdullah University of Science and Technology (KAUST). I use this webspace for hosting personal projects, and plan to publish some of them publicly here.


08/19/2019 I’m joining Waymo!
05/30/2019 Graduated from Harvard University with a Master’s degree in Computational Science and Engineering
04/30/2019 One paper accepted at Robotics: Science and Systems (RSS’19): “OIL: Observational Imitation Learning”
04/16/2019 We will present a paper at VOCVALC, CVPR’19: Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics
04/06/2019 We will present a paper at UAVISION, CVPR’19: Learning a Controller Fusion Network by Online Trajectory Filtering
02/01/2019 Presented our struct2depth work at AAAI-19 in Hawaii
01/23/2019 Gave a workshop on “Convolutional Autoencoders for Image Manipulation” at ComputeFest 2019
12/16/2018 Preprint of our work on Connectomics now on arXiv
11/28/2018 New project released: OIL: Observational Imitation Learning
11/27/2018 New blog post on our struct2depth work on Google’s AI blog
11/19/2018 The code for our struct2depth paper is now part of the TensorFlow models repository: Link
11/01/2018 One paper accepted to AAAI’19: “Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos” (full text)
10/06/2018 Joined the MIT Computational Perception & Cognition Lab, led by Aude Olivia
09/08/2018 We won the best paper award at UAVISION 2018
08/03/2018 We are presenting our work on autonomous drone racing on Sept 8 at UAVISION, ECCV’18
05/29/2018 Started internship in the Google Brain Robotics group
05/22/2018 Our new datasets for connectomics research are now publicly available: Kasthuri++ and Lucchi++
05/21/2018 Release of new tutorial for Bayesian GAN
02/08/2018 Started new project on Connectomics with the Visual Computing Group (VCG)
01/22/2018 Started new collaboration with the Center for Clinical Data Science (CCDS)
11/23/2017 One paper accepted to IJCV: “Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications” (full text)
10/21/2017 Official release of Sim4CV, our simulation environment for Computer Vision
09/01/2017 Started Master’s program in Computational Science and Engineering
08/19/2017 New paper released on arXiv: “Autonomous UAV Racing Using Deep Learning
05/24/2017 Recipient of German Academic Scholarship Foundation US-Scholarship (Studienstiftung)
03/28/2017 Recipient of DAAD Graduate Scholarship