Name: Barbara Rössle
Position: Ph.D Candidate
E-Mail: barbara.roessle@tum.de
Phone: +49 (89) 289 - 18164
Room No: 02.07.038

Bio

My name is Barbara and I am a PhD student in the Visual Computing Lab. Prior to that, I was developing software for autonomous driving at BMW, focusing on localization and sensor fusion. My master thesis was on vehicle localization in 6 degrees of freedom for augmented reality. I studied computer science (M.Sc.) and electrical engineering (B.Eng.) at the Universities of Applied Sciences in Ulm and Esslingen. As part of my studies, I spent a semester at Hacettepe University in Ankara, Turkey.

Research Interest

Novel view synthesis, neural rendering, domain adaptation

Publications

Preprints

End2End Multi-View Feature Matching using Differentiable Pose Optimization
Barbara Roessle, Matthias Nießner
arXiv
We connect feature matching and pose optimization in an end-to-end trainable pipeline that enables matches and confidence weights to be informed by the pose estimation objective. To this end, we introduce GNN-based multi-view feature matching to inform pose optimization with a differentiable pose solver, which increases both pose estimation and matching accuracy.
[video][bibtex][project page]

2022

Dense Depth Priors for Neural Radiance Fields from Sparse Input Views
Barbara Roessle, Jonathan T. Barron, Ben Mildenhall, Pratul P. Srinivasan, Matthias Nießner
CVPR 2022
We leverage dense depth priors for recovering neural radiance fields (NeRF) of complete rooms when only a handful of input images are available. First, we take advantage of the sparse depth that is freely available from the structure from motion preprocessing. Second, we use depth completion to convert these sparse points into dense depth maps and uncertainty estimates, which are used to guide NeRF optimization.
[video][bibtex][project page]