| A case for using rotation invariant features in state of the art feature matchers G Bökman, F Kahl Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 29 | 2022 |
| RoMa: Revisiting Robust Losses for Dense Feature Matching J Edstedt, Q Sun, G Bökman, M Wadenbäck, M Felsberg arXiv preprint arXiv:2305.15404, 2023 | 13 | 2023 |
| Zz-net: A universal rotation equivariant architecture for 2d point clouds G Bökman, F Kahl, A Flinth Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 13 | 2022 |
| DeDoDe: Detect, Don't Describe--Describe, Don't Detect for Local Feature Matching J Edstedt, G Bökman, M Wadenbäck, M Felsberg arXiv preprint arXiv:2308.08479, 2023 | 8 | 2023 |
| Rigidity preserving image transformations and equivariance in perspective L Brynte, G Bökman, A Flinth, F Kahl Scandinavian Conference on Image Analysis, 59-76, 2023 | 4 | 2023 |
| Investigating how ReLU-networks encode symmetries G Bökman, F Kahl Advances in Neural Information Processing Systems 36, 2024 | 2 | 2024 |
| Azimuthal rotational equivariance in spherical convolutional neural networks C Toft, G Bökman, F Kahl 2022 26th International Conference on Pattern Recognition (ICPR), 3808-3814, 2022 | 2 | 2022 |
| Steerers: A framework for rotation equivariant keypoint descriptors G Bökman, J Edstedt, M Felsberg, F Kahl arXiv preprint arXiv:2312.02152, 2023 | 1 | 2023 |
| DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector J Edstedt, G Bökman, Z Zhao arXiv preprint arXiv:2404.08928, 2024 | | 2024 |
| Leveraging Cutting Edge Deep Learning Based Image Matching for Reconstructing a Large Scene from Sparse Images G Bökman, J Edstedt arXiv preprint arXiv:2310.01092, 2023 | | 2023 |
| In search of projectively equivariant networks G Bökman, A Flinth, F Kahl arXiv preprint arXiv:2209.14719, 2022 | | 2022 |
Fredrik KahlProfessor, Chalmers University of TechnologyVerified email at chalmers.se
