Name: Andreas Rössler
Position: Ph.D Candidate
E-Mail: andreas.roessler@tum.de
Phone: +49-89-289-19595
Room No: 02.13.035

Bio

I recieved my Bachelor's (2013) and Master's degree (2016) in Mathematics at the University of Regenbsurg before starting my career in computer vision. After an internship at the chair of Prof. Matthias Niessner, where I researched generative models, I am now a first year Ph.D. student with a focus on forgery detection as well the creation of tampered images and videos. Additionally, I am a tutor and guest lecturer for the class "Deep Learning for Computer Vision" at TUM.

Research Interest

Forensics, Deep Learning with 4D shapes (in spatial and temporal domains), Reinforcement Learrning, (Conditional) Generative Models

Publications

2019
FaceForensics++: Learning to Detect Manipulated Facial Images
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner
ICCV 2019
In this paper, we examine the realism of state-of-the-art facial image manipulation methods, and how difficult it is to detect them - either automatically or by humans. In particular, we create a datasets that is focused on DeepFakes, Face2Face, FaceSwap, and Neural Textures as prominent representatives for facial manipulations.
[video][code][bibtex][project page]
2018
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
Davide Cozzolino, Justus Thies, Andreas Rössler, Christian Riess, Matthias Nießner, Luisa Verdoliva
arXiv 2018
ForensicTransfer tackles two challenges in multimedia forensics. First, we devise a learning-based forensic detector which adapts well to new domains, i.e., novel manipulation methods. Second we handle scenarios where only a handful of fake examples are available during training.
[bibtex][project page]
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner
arXiv 2018
In this paper, we introduce FaceForensics, a large scale video dataset consisting of 1004 videos with more than 500000 frames, altered with Face2Face, that can be used for forgery detection and to train generative refinement methods.
[video][bibtex][project page]