David Nordström
PhD Student in Deep Learning
I like Deep Learning and Computer Vision. Make GPUs go brrr.
Supervised by Prof. Fredrik Kahl and Dr. Georg Bökman.
News
Pre-prints out now for MuM and RoMa v2
Released our work on Multi-View Masked Image Modeling for 3D Vision and a new dense feature matcher, RoMa v2.
ICML 2025 Spotlight
"Flopping for FLOPs" accepted as Spotlight Paper at ICML 2025.
Publications
MuM: Multi-View Masked Image Modeling for 3D Vision
David Nordström, Johan Edstedt, Fredrik Kahl, Georg Bökman
MuM is a feature encoder tailored for 3D vision. We extend the MAE objective to arbitrarily many frames and show that when scaling this we can beat DINOv3 and CroCo v2 on matching, feedforward reconstruction, and relative pose estimation.
RoMa v2: Harder Better Faster Denser Feature Matching
Johan Edstedt, David Nordström, Yushan Zhang, Georg Bökman, Jonathan Astermark, Viktor Larsson, Anders Heyden, Fredrik Kahl, Mårten Wadenbäck, Michael Felsberg
RoMa v2 is a dense feature matcher that combines speed with diverse data and novel architecture and matching loss. The result is a state-of-the-art model that excels on a wide range of tasks.
Octic Vision Transformers: Quicker ViTs Through Equivariance
David Nordström, Johan Edstedt, Fredrik Kahl, Georg Bökman
Introducing octic-equivariant Vision Transformers, achieving 40% FLOPs reduction while improving both classification and segmentation performance for DeiT III and DINOv2.
Education
PhD in Geometric Deep Learning and 3D Computer Vision
Chalmers University of Technology
Research focus on equivariant neural networks, efficient deep learning architectures and 3D computer vision.
M.Sc. in Engineering Mathematics
Chalmers University of Technology
International Experience
Exchange Semester at UC Berkeley
Exchange Semester at Seoul National University
B.Sc. in Industrial Engineering
Chalmers University of Technology
B.Sc. in Economics
University of Gothenburg
Completed in parallel with Industrial Engineering degree
Teaching
Computer Vision
EEN020, Chalmers University of Technology
Deep Machine Learning
SSY340, Chalmers University of Technology
Talks
Feedforward 3D Reconstruction
Guest lecture in the Computer Vision course at Chalmers University of Technology.
Get in Touch
I'm always open to research collaborations and discussions.
Feel free to reach out via email for any inquiries or opportunities.