In fields such as animal conservation, ethology, and neuroscience, the tracking and understanding of animals and their behavior is key. Today, this is often done manually. We are creating a new generation of tools, using machine learning, that will automate and revolutionize the analysis of animal behavior.
Project: Our goal is to create 3D models of animal shape that are anatomically correct and to use such models to track and analyze animal behavior. The project combines methods from machine learning, computer vision, and graphics to learn animal models from unique datasets containing volumetric scans, multi-view imagery, and videos. The challenges include:
- Registering multimodal data: volumes, meshes, point-clouds, images and videos.
- Learning shape models that can capture shape and motion variation across animals that can be related to individual attributes such as age.
- Representing the relation between internal structures such as the skeleton and organs and the external body surface.
- Performing articulated tracking of animals in complex, natural, scenarios.
Scientific Context: The student will be part of the Perceiving Systems Department (https://ps.is.tuebingen.mpg.de/), which is a world leader on the statistical modeling of humans and animals from data, in the fields of computer vision, computer graphics and machine learning, with publications in major venues such as CVPR, ICCV, ECCV and SIGGRAPH.
For related work please visit https://ps.is.tue.mpg.de/research_projects/capturing-animal-shape.
The student will collaborate closely with Sergi Pujades (University Grenoble Alpes – INRIA Grenoble, France), Silvia Zuffi (IMATI-CNR in Milano, Italy) and be locally advised by Michael Black. A surrounding team of approx. 10 PhDs, 6 senior researches and 4 engineers will be available for interactions, discussions, and possible collaboration.
Candidate: We seek candidates with a deep interest in Computer Vision, Computer Graphics and Machine Learning. The successful candidate will have:
- a strong Master’s degree in computer science or another area related to Computer Vision, Computer Graphics and Machine Learning
- excellent written and oral communication skills (English)
- excellent software skills
- preliminary experience in related topics such as 3D meshes and pointcloud processing, neural networks, classical optimization, etc.
Location and mobility: The PhD research will be centered in Tübingen (Germany) with possible visits to Grenoble (France) and Milano (Italy).
The PhD student (m/f/d) will receive a PhD funding contract equivalent in remuneration to pay group E13, 65% of the Collective Wage Agreement for the Public Service. An initial contract will be given for 3 years with possibility of 1-year extension.
Application: Please apply through the IMPRS program (https://imprs.is.mpg.de/application). Please mention Michael Black, Sergi Pujades and Silvia Zuffiin your application. The application deadline is November 6th, 2019 at 11:59am CET for a start in 2020.
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 seeks to increase the number of women in those areas where they are underrepresented and therefore explicitly encourages women to apply.