Ludvig Dillén
I am a 3rd year PhD student in Computer Vision and Machine Learning at the Centre of Mathematical Sciences at Lund University under the supervision of Viktor Larsson and co-supervision of Magnus Oskarsson. I am funded by ELLIIT and affiliated with WASP.
I research on localization and mapping problems in computer vision, including structure from motion, point cloud registration, structureless and sparse-view localization, as well as scene coordinate regression/reconstruction. In addition to research, I teach undergraduate and graduate courses in mathematics, computer vision, and machine learning, and pursue advanced coursework in these areas to deepen my knowledge.
I am always open to collaborations on projects related to 3D vision, and in particular image-based localization, mapping, and learning good representations. Feel free to reach out!
news
| May 2026 | Second place in Structured Semantic 3D Reconstruction (S23DR) Challenge 2026 (paper, code) |
|---|---|
| Feb 2026 | Active Exploration for Sparse Visual Localization accepted at CVPR findings track (paper, supp, code) |
| Feb 2026 | Sparse–View Localization via Online Neural 3D Regression accepted at CVPR (paper, supp, poster, video, code) |
| Mar 2025 | FACT: Multinomial Misalignment Classification for Point Cloud Registration accepted at SCIA (paper+supp, code) |
| Oct 2023 | Finished Civil Engineering at Linköping University with MSc in Computer Vision and Signal Analysis with GPA 4.92/5.00 and Feature-Aware Point Transformer for Point Cloud Alignment Classification |