EMAIL | RÉSUMÉ | LINKEDIN | GITHUB | TWITTER | SCHOLAR
I write reproducible papers with solutions to real-world problems
Postdoc at Amazon working on Multimodal Large Language Models.
Previously I was a visitor at Carnegie Mellon University's AirLab with Prof. Sebastian Scherer and an intern at Amazon,
during my PhD at Polytechnic of Turin with Prof. Barbara Caputo.
Before my PhD I worked at the Italian Institute of Technology.
TLDR: Computer Vision PhD with 7 first-author CVPR / ICCV / ECCV papers, ~1000 GitHub stars
03/2025: | Started a new job as a Postdoc at Amazon! I'll be working on Multimodal Large Language Models |
07/2024: | MeshVPR is accepted at ECCV 2024! |
06/2024: | Went to CVPR to present EarthLoc (poster), EarthMatch (workshop oral) and MeshVPR (demo)! |
03/2024: | Going for a 4-months visiting to Carnegie Mellon University's AirLab under the supervision of Professor Sebastian Scherer. |
03/2024: | EarthLoc is accepted at CVPR 2024! EarthLoc is now used by NASA to localize photos from the International Space Station. |
01/2024: | Gave a talk at the Czech Technical University on the applications and challenges of visual geo-localization! |
07/2023: | Two first-author papers accepted at ICCV! |
07/2023: | I won the first prize for the Best Student Research in the Video&Poster Competition at EuroCon 2023 |
07/2023: | I gave an invited talk to the Pattern Analysis and Computer Vision group at the Italian Institute of Technology in Genova on the current state of scalable visual geolocalization. |
06/2023: | I gave a 30 minutes invited talk at CVPR 2023 for the tutorial A Comprehensive Tour and Recent Advancements toward Real-world Visual Geo-Localization. |
06/2023: | Our demo on using 3D models for geolocalizing images has been accepted to ICCV 2023 |
06/2022: | The RoboTo robotics team (for which I'm doing the computer vision / object detection part) achieved 5th place in the 1 vs 1 competition at the finals of the Robomaster University League in Seattle! |
05/2023: | I gave an invited talk at MaLGa on the current state of Visual Place Recognition. |
04/2023: | Our paper on local features and re-ranking methods for Visual Place Recognition has been accepted to the Image Matching Workshop at CVPR 2023 |
06/2022: | I gave an Oral presentation at CVPR 2022 for our Deep Visual Geo-localization Benchmark paper |
06/2022: | One paper on Sequence-based Visual Place Recognition accepted to IROS 2022! |
06/2022: | The RoboTo robotics team (for which I'm doing the computer vision / object detection part) qualified for the finals of the Robomaster University League in Texas! |
05/2022: | I started a 4 months internship at Amazon Berlin as an Applied Scientist Intern, working on multi-model video action recognition and segmentation. |
03/2022: | Two first-author papers accepted to CVPR 2022! One paper presenting a SOTA geolocalization / visual place recognition method called CosPlace, and one Oral paper presenting a thorough benchmark on the same task. |
07/2021: | Our paper on "Viewpoint Invariant Dense Matching for Visual Geolocalization" was accepted to ICCV 2021! |
10/2020: | Our paper on Domain Adaptation for Geolocalization accepted at WACV 2021! |
MeshVPR: Citywide Visual Place Recognition Using 3D Meshes
ECCV 2024
ArXiv | Code | Data | Website | Bibtex@InProceedings{Berton_ECCV_2024_MeshVPR, author = {Gabriele Berton and Lorenz Junglas and Riccardo Zaccone and Thomas Pollok and Barbara Caputo and Carlo Masone}, title = {MeshVPR: Citywide Visual Place Recognition Using 3D Meshes}, booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)}, month = {October}, year = {2024}, }
EarthLoc: Astronaut Photography Localization by Indexing Earth from Space
CVPR 2024
Website | ArXiv | Proceedings | Code and Data | Bibtex@InProceedings{Berton_CVPR_2024_EarthLoc, author = {Berton, Gabriele and Stoken, Alex and Caputo, Barbara and Masone, Carlo}, title = {EarthLoc: Astronaut Photography Localization by Indexing Earth from Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, }
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
ICCV 2023
ArXiv | Proceedings | Code | Bibtex@inProceedings{Berton_ICCV_2023_EigenPlaces, author = {Gabriele Berton, Gabriele Trivigno, Carlo Masone, Barbara Caputo}, title = {EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition}, booktitle = {ICCV}, month = {October}, year = {2023}, }
Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-localization
ICCV 2023
ArXiv | Proceedings | Code | Bibtex@inProceedings{Berton_ICCV_2023_DivideClassify, author = {Gabriele Trivigno, Gabriele Berton, Carlo Masone, Barbara Caputo}, title = {Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-localization}, booktitle = {ICCV}, month = {October}, year = {2023}, }
Rethinking Visual Geo-localization for Large-Scale Applications
CVPR 2022
ArXiv | Proceedings | Code and Data | Bibtex@inProceedings{Berton_CVPR_2022_cosPlace, author = {Gabriele Berton, Carlo Masone, Barbara Caputo}, title = {Rethinking Visual Geo-localization for Large-Scale Applications}, booktitle = {CVPR}, month = {June}, year = {2022}, }
Deep Visual Geo-localization Benchmark
CVPR 2022 (Oral)
ArXiv | Proceedings | Code | Data | Bibtex@inProceedings{Berton_CVPR_2022_benchmark, author = {Gabriele Berton, Riccardo Mereu, Gabriele Trivigno, Carlo Masone, Gabriela Csurka, Torsten Sattler, Barbara Caputo}, title = {Deep Visual Geo-localization Benchmark}, booktitle = {CVPR}, month = {June}, year = {2022}, }
Viewpoint Invariant Dense Matching for Visual Geolocalization
ICCV 2021
ArXiv | Proceedings | Code | Bibtex@inProceedings{Berton_ICCV_2021, author = {Gabriele Berton, Carlo Masone, Valerio Paolicelli, Barbara Caputo}, title = {Viewpoint Invariant Dense Matching for Visual Geolocalization}, booktitle = {ICCV}, month = {October}, year = {2021}, pages = {12169-12178} }
AstroLoc: Robust Space to Ground Image Localizer
CVPR 2025 Demo
ArXiv | Website & Demo | Bibtex@misc{Berton_2025_AstroLoc, title={AstroLoc: Robust Space to Ground Image Localizer}, author={Gabriele Berton and Alex Stoken and Carlo Masone}, year={2025}, eprint={2502.07003}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.07003}, }
Megaloc: One retrieval to place them all
CVPR 2025 Demo
ArXiv | Code & Demo | Bibtex@misc{Berton_2025_MegaLoc, title={MegaLoc: One Retrieval to Place Them All}, author={Gabriele Berton and Carlo Masone}, year={2025}, eprint={2502.17237}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2502.17237}, }
MeshVPR: Citywide Visual Place Recognition Using 3D Meshes
CVPR 2024 Demo
ArXiv | Code | Data | Website | Bibtex@article{Berton_2024_MeshVPR, title={MeshVPR: Citywide Visual Place Recognition Using 3D Meshes}, author={Gabriele Berton and Lorenz Junglas and Riccardo Zaccone and Thomas Pollok and Barbara Caputo and Carlo Masone}, year={2024}, eprint={2406.02776}, archivePrefix={arXiv}, }
EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography
CVPR 2024 Workshop
Website | ArXiv | Proceedings | Code | Data | Matching Code | Bibtex@InProceedings{Berton_2024_EarthMatch, author = {Gabriele Berton, Gabriele Goletto, Gabriele Trivigno, Alex Stoken, Barbara Caputo, Carlo Masone}, title = {EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, }