B04 | Adaptive Algorithms for Motion Estimation

Prof. Andrés Bruhn, University of Stuttgart
Email | Website

Andrés Bruhn

Prof. Albrecht Schmidt, LMU Munich
Email | Website

Albrecht Schmidt

Project B04

Noah Berenguel Senn, University of Stuttgart – Email | Website

Jenny Schmalfuß, University of Stuttgart –  Email | Website

This project aims at developing novel algorithms for optical flow (2D motion) and scene flow (3D motion) estimation. Instead of relying on fixed assumptions, the goal is to adaptively integrate prior knowledge and other available information in order to design approaches that are not only highly accurate but also generalize well across datasets.

Fig. 1: Optical flow estimation on the automotive KITTI dataset using the method of Maurer et al. (BMVC 2018).

Research Questions

How can we develop algorithms for adaptive motion estimation of high accuracy and generalizability that are applicable in the wild?

To which extent can concepts be generalized from the 2D to the 3D domain and how can additional constraints imposed by the 3D world improve the estimation?

How can we transfer the benefits of adaptive algorithms to specific applications?

Project Group A

Models and Measures

 

Completed

 

Project Group B

Adaptive Algorithms

 

Completed

 

Project Group C

Interaction

 

Completed

 

Project Group D

Applications

 

Completed