Fabian Mentzer

Updates on Twitter
Code on GitHub
Publications below
Blog Posts below
Music on YouTube and SoundCloud (nerodiseppia.ch) 🎵 🎹

Publications

Google Scholar
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context arXiv
Gemini Team
arxiv (2024)
GIVT: Generative Infinite-Vocabulary Transformers arXiv
Michael Tschannen, Cian Eastwood, Fabian Mentzer
ECCV 2024
Finite Scalar Quantization: VQ-VAE Made Simple arXiv
Fabian Mentzer, David Minnen, Eirikur Agustsson, Michael Tschannen
ICLR 2024
High-Fidelity Image Compression with Score-based Generative Models arXiv
Emiel Hoogeboom, Eirikur Agustsson, Fabian Mentzer, Luca Versari, George Toderici, Lucas Theis
preprint (2023)
M2T: Masking Transformers Twice for Faster Decoding arXiv
Fabian Mentzer, Eirikur Agustsson, Michael Tschannen
ICCV 2023
Multi-Realism Image Compression with a Conditional Generator arXiv
Eirikur Agustsson, David Minnen, George Toderici, Fabian Mentzer
CVPR 2023
Lossy Compression with Gaussian Diffusion arXiv
Lucas Theis, Tim Salimans, Matthew D. Hoffman, Fabian Mentzer
ArXiv (2022)
VCT: A Video Compression Transformer arXiv
Fabian Mentzer, George Toderici, David Minnen, Sung-Jin Hwang, Sergi Caelles, Mario Lucic, and Eirikur Agustsson
NeurIPS 2022
Neural Video Compression using GANs for Detail Synthesis and Propagation arXiv
Mentzer*, Fabian, Agustsson*, Eirikur, Ballé, Johannes, Minnen, David, Johnston, Nick, and Toderici, George
ECCV 2022
High-Fidelity Generative Image Compression Demo arXiv
Mentzer, Fabian, Toderici, George, Tschannen, Michael, and Agustsson, Eirikur
NeurIPS 2020 (Oral)
Learning better lossless image compression using lossy compression arXiv
Mentzer, Fabian, Van Gool, Luc, and Tschannen, Michael
CVPR 2020
Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement arXiv
Yang, Ren, Mentzer, Fabian, Van Gool, Luc, and Timofte, Radu
CVPR 2020
Practical full resolution learned lossless image compression arXiv
Mentzer, Fabian, Agustsson, Eirikur, Tschannen, Michael, Timofte, Radu, and Van Gool, Luc
CVPR 2019 (Oral)
Generative adversarial networks for extreme learned image compression arXiv
Agustsson*, Eirikur, Tschannen*, Michael, Mentzer*, Fabian, Timofte, Radu, and Van Gool, Luc
ICCV 2019
Towards image understanding from deep compression without decoding arXiv
Torfason, Róbert, Mentzer, Fabian, Agustsson, Eirikur, Tschannen, Michael, Timofte, Radu, and Van Gool, Luc
ICLR 2018
Conditional probability models for deep image compression arXiv
Mentzer*, Fabian, Agustsson*, Eirikur, Tschannen, Michael, Timofte, Radu, and Van Gool, Luc
CVPR 2018
Deep structured features for semantic segmentation arXiv
Tschannen, Michael, Cavigelli, Lukas, Mentzer, Fabian, Wiatowski, Thomas, and Benini, Luca
EUSIPCO 2017
Soft-to-hard vector quantization for end-to-end learning compressible representations arXiv
Agustsson, Eirikur, Mentzer, Fabian, Tschannen, Michael, Cavigelli, Lukas, Timofte, Radu, Benini, Luca, and Van Gool, Luc
NIPS 2017