I'm a doctoral CLS Fellow under joint supervision of Prof. Konrad Schindler and Prof. Michael Black. Before that I've received a Bachelor as well as a Master's Degree in Mechanical Engineering from ETH Zurich. I'm working at the intersection between Computer Vision and Machine Learning. Specifically, I focus on 3D human shape and pose estimation and have strong interests in unsupervised learning. I aim to find a good balance between labeling effort and performance.
In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), pages: 5561-5569, Febuary 2020 (inproceedings)
The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision is available, but in problems like human pose and shape estimation, it is difficult to obtain natural images with 3D ground truth. To go one step further, we propose a new architecture that facilitates unsupervised, or lightly supervised, learning. The idea is to break the problem into a series of transformations between increasingly abstract representations. Each step involves a cycle designed to be learnable without annotated training data, and the chain of cycles delivers the final solution. Specifically, we use 2D body part segments as an intermediate representation that contains enough information to be lifted to 3D, and at the same time is simple enough to be learned in an unsupervised way. We demonstrate the method by learning 3D human pose and shape from un-paired and un-annotated images. We also explore varying amounts of paired data and show that cycling greatly alleviates the need for paired data. While we present results for modeling humans, our formulation is general and can be applied to other vision problems.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems