Published:
Official implementation for DeepViewAgg. This codebase holds tools for multimodal learning on 2D images 🖼️ and 3D point clouds ☁️️. In particular, we developed an efficient and scalable framework for learning to densely map and aggregate multi-view image features to point clouds.
Published:
The pgeof library provides utilities for fast, parallelized computing ⚡ of local geometric features for 3D point clouds ☁️ on CPU. It was initially introduced as a dependency for Superpoint Transformer.
Published:
A python-populated Notion template to help you keep track of the papers you read 📜, their authors 👤, your notes 📝, and more 🔥. This is my personal framework for getting the best of Zotero but in Notion.
Published:
Official implementation for Superpoint Transformer, SuperCluster, and EZ-SP. This codebase holds tools for efficient, scalable superpoint-based learning 🧩.
Published:
torch-graph-components holds algorithms for fast graph connected components and graph partitioning, fully implemented in PyTorch with GPU parallelization in mind. In particular, this project contains the graph components and graph partitioning algorithms introduced in EZ-SP.
Published:
DeepViewAgg was accepted for an oral at CVPR’22
Published:
DeepViewAgg shortlisted as best paper finalist at CVPR'22
Published:
Best of CVPR issue — CV News interview
Published:
Superpoint Transformer was accepted at ICCV’23
Published:
SuperCluster was accepted for an oral at 3DV’24
Published:
PhD defense at IGN in presence of Cédric Demonceaux, Sébastien Lefèvre, Patrick Pérez, Siyu Tang, Duygu Ceylan, Loïc Landrieu, and Bruno Vallet
Published:
Joined the EcoVision lab at University of Zurich as a postdoctoral researcher
Published:
Gave a workshop tutorial on Superpoint Transformer hosted by Florent Poux
Published:
Nominated as ECCV'24 outstanding reviewer
Published:
Teja Kattenborn visit to EcoVision
Published:
Kaan Karaman will present GSR4B at the ISPRS GSW'25
Published:
Received the AFRIF 2024 PhD Award accessit
Published:
Loic Landrieu visit to EcoVision and ETH AI Center
Published:
Emilia Arens and Johannes Dollinger will present our research on Deep Species Distribution Modeling at the LPS'25
Published:
Valerio Marsocci visit to EcoVision
Published:
Released torch-graph-components, which isolates the core graph algorithms from EZ-SP
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in CVPR, 2022
Published in ICCV, 2023
Published in 3DV, 2024
Published in Universite Gustave Eiffel, 2024
Published in IEEE Geoscience and Remote Sensing Magazine, 2025
Published in ISPRS Geospatial Week, 2025
Published in ICLR - Tackling Climate Change with Machine Learning workshop, 2025
Published in CVPR - EarthVision workshop, 2025
Published in PFG--Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2025
Published in ICRA, 2026
Published in CVPR, 2026
Published in arxiv, 2026
Published:
Presenting DeepViewAgg at the IGN-ENSG Research Days
Published:
Presenting DeepViewAgg at the GDR ISIS research group seminar
Published:
Presenting DeepViewAgg at the IGN-ENSG Research Days
Published:
Presenting DeepViewAgg at the AI4GEO project seminar
Published:
Tutorial 3D Deep Learning, Torch-Points3D & DeepViewAgg at ENGIE Lab CRIGEN
Published:
Presenting DeepViewAgg to the Ecole Polytechnique, LIX lab
Published:
Presenting DeepViewAgg at CVPR'22 - Best Paper finalist 🎉
Published:
Had the honor to be interviewed for the CV News Best of CVPR issue
Published:
Presenting DeepViewAgg to the Ecole des Ponts, IMAGINE lab
Published:
Presenting DeepViewAgg at ISPRS'22
Published:
Presenting DeepViewAgg at ICVSS'22
Published:
Presenting IGN's research on Large-Scale 2D and 3D Learning to the German Federal Agency for Cartography and Geodesy (BKG)
Published:
Presenting Superpoint Transformer to the University of Zürich, EcoVision lab
Published:
Presenting Superpoint Transformer to the Samp R&D lab
Published:
Presenting Superpoint Transformer to the Valeo.ai lab
Published:
Presenting Superpoint Transformer to the ENGIE Lab CRIGEN
Published:
Presenting Superpoint Transformer at ICCV'23
Published:
Presenting Superpoint Transformer to the ETH Zürich, Computer Vision and Geometry lab
Published:
Presenting Superpoint Transformer to the ETH Zürich, Photogrammetry and Remote Sensing lab
Published:
Presenting IGN's research on Large-Scale 2D and 3D Learning to the National Land Survey of Finland (NSL)
Published:
Presenting SuperCluster to the Ecole des Ponts, IMAGINE lab
Published:
PhD defense on Efficient Learning on Large-Scale 3D Point Clouds at IGN, in presence of Sébastien Lefèvre, Cédric Demonceaux, Patrick Pérez, Siyu Tang, Duygu Ceylan, Loic Landrieu, and Bruno Vallet 🎓
Published:
Presenting SuperCluster at 3DV'24 - Oral 🎉
Published:
Presenting Superpoint Transformer to the GeoDigital R&D team
Published:
Presenting EcoVision research to Google DeepMind
Published:
Presenting EcoVision research to the Una Europa alliance
Published:
Workshop tutorial on Superpoint Transformer hosted by Florent Poux
Published:
Presenting SuperCluster to the Samp R&D lab
Published:
Presenting EcoVision research to the WSL Dynamic Ecology group
Published:
Presenting Deep Species Distribution Modeling to the CNES COMET TSI
Published:
Presenting Superpoint Transformer and EcoVision research to the NVIDIA Strategic Research Engagement
Published:
Presenting Superpoint Transformer to the Unil. Institue for Forensic Science
Published:
Presenting EcoVision research to NatureFinance
Published:
Presenting SSL4Eco at CVPR'25 EarthVision
Published:
Presenting EcoVision research to the ETH Plant Ecology group
Published:
Presenting Embed2Scale and EcoVision research to Global Forest Watch and Land & Carbon Lab reseachers
Published:
Presenting EcoVision research to the MPI of Animal Behavior
Published:
Presenting Embed2Scale and EcoVision research to ESA Φ-lab
Published:
Presenting Deep learning on 3D point clouds at the UZH RSL Remote Sensing Colloquium
Published:
Presenting Forest Disturbance Monitoring with Geospatial Foundation Models at EGU'26
Published:
Tutorial Building Earth Observation Embedding Workflows with TerraTorch IBM Research at ESA-NASA workshop on AI Foundation Model for EO