Researcher for Statistical 3D Model of Quadrupeds (f/m/div)

 

The Optics and Sensing Laboratory at the Max Planck Institute for Intelligent Systems in Tübingen has an open position for a Researcher to join the ongoing research efforts in the development of statistical 3D models of Horses.

 

About the Max Planck Institute for Intelligent Systems

They are creating the world’s most realistic human and animal avatars for use in research, film, virtual reality, biology and medicine. Using unique 3D & 4D capture facilities, machine learning, computer vision and advanced graphics, they are modeling every nuance of how humans and animals look and move. They develop algorithms to estimate human shape and motion in images, videos and RGB-D sequences. Their approaches define the current state of the art, and they are constantly pushing these methods and systems in order to achieve a better accuracy. Their future work aims at generating automatic 3D pose, shape and texture of animals from images acquired in-the-wild.

Department website: https://is.mpg.de/oslab

 

The Project

This project is aimed at bridging the gap between newly developed state of the art statistical model(s) for quadrupeds, and the physical word. They are collaborating with the Swedish University of Agricultural Sciences and National Research Council of Italy to develop anatomically accurate 3D model, which can be used for biological applications based on one of the biggest datasets of animal scans.

 

Your Tasks

Your task will be to create a method for extracting mesh representations of shape and pose from image data by leveraging existing methods and/or developing novel approaches, as part of the larger goal of bringing our model(s) into active adoption. Specifically, this includes (but is not limited to):

1. Creation of generative methods for hyperrealistic scenes and extraction of high-fidelity novel views.

2. Training of multi-view and single-view mesh extraction models,

3. Validation of the method in a real-life biological context,

 

Skills and requirements

• Strong background in computer vision, with particular experience in human and animal shape modeling
• Experience with 3D vision topics such as 3D mesh models, statistical shape modeling and articulated pose estimation
• Solid ML/AI foundation
• Strong programming skills in Python (CUDA is a plus)
• Hands-on experience with 3D and image-based computer vision
• Experience implementing 3D computer vision algorithms and training end-to-end machine learning models (from data collection and design to evaluation)
• Knowledge and practical experience with deep learning, including frameworks such as PyTorch
• MSc is required in addition a few years of job experience or PhD
• Good oral and written communication skills in English

 

What they offer

In this working environment, you will be exposed to cutting-edge technologies related to computer vision and multi-sensor systems. The MPI for Intelligent Systems is one of the world's leading research institutions for machine learning, computer vision and robotics, and studying the concepts of intelligence and autonomous behavior in artificial systems at different length scales. The position is ideally suited for candidates looking to extend their scientific and cultural horizons particularly in the area of 3D Motion Capture. You will be a part of a dynamic team of international scientists, engineers, and administrative staff. This is a position limited to 12 months and the expected starting date is as soon as possible with a possibility of extension.

The Max Planck Society is committed to increasing the number of individuals with disabilities in its workforce and therefore encourages applications from such qualified individuals. The Max Planck Society strives for gender equality and diversity. Furthermore, the Max Planck Society seeks to increase the number of women in its workforce in those areas where they are underrepresented and therefore explicitly encourages women to apply.

The position is available as of now and will be open until filled or no longer needed.

 

Contact and application

Any questions regarding the position should be forwarded to Keiko Kitagawa at keiko.kitagawa@tuebingen.mpg.de and Dr. Senya Polikovsky at senya.polikovsky@tue.mpg.de

Candidates should send their:

1. Curriculum Vitae

2. 2 References (with contact information)

3. GitHub account or other sites showing us your programming skills

4. One-page document that answers the following questions:

a. Briefly explain some of the challenges in mapping 2D to 3D shapes and how your approach would be in tacking the challenge.

b. How are the pose-dependent deformations represented in the VAREN model (https://varen.is.tue.mpg.de/) and how does this differ from the SMPL model?

Please upload the requested documents as a single application package, in a single PDF file to the application portal. Only complete applications with the documents including the letter can be considered. The position will be open until filled.

If you prefer to send a hardcopy application, you may do so. Please send it to: MPI-IS, Keiko Kitagawa, Max-Planck-Ring 4, 72076 Tübingen.