Hey there!

I am Mathias Parger. I live in Graz, Austria - the city in which I also did my studies in computer science. I created this page to share my research with you, and to add some context and personal stories to the projects. My main fields of interest include machine learning, computer vision, and computer graphics - typically with a focus on efficiency and performance. I love to make stuff go faster, and I think that performance is often the foundation for innovation - by removing constraints that hold back progress.

Latest Posts See all

paper

Collaborative Control for Geometry-Conditioned PBR Image Generation
Shimon Vainer, Mark Boss, Mathias Parger, Konstantin Kutsy, Dante De Nigris, Ciara Rowles, Nicolas Perony, Simon Donné

Collaborative Control for Geometry-Conditioned PBR Image Generation teaser

January 2023, with the PhD in my pocket, I joined Unity to work on real-time NeRFs. It sounded like the perfect job - I am a big video game enthusiast and already...

Read More

paper

MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions
Mathias Parger, Chengcheng Tang, Thomas Neff, Christopher D Twigg, Cem Keskin, Robert Wang, Markus Steinberger

MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions teaser

MotionDeltaCNN is a follow-up paper to DeltaCNN and the last of the three research collaborations I did with Meta Reality Labs. This is probably a good time to thank them for...

Read More

paper

DeltaCNN: End-to-end CNN inference of sparse frame differences in videos
Mathias Parger, Chengcheng Tang, Christopher D Twigg, Cem Keskin, Robert Wang, Markus Steinberger

DeltaCNN: End-to-end CNN inference of sparse frame differences in videos teaser

DeltaCNN was my favorite project during my PhD. It’s the second research collaboration with the great team at Meta Reality Labs, and the topic is a perfect match for my skills and...

Read More

All Posts

Contact

Reach out via social media, preferably LinkedIn.