Summary

As a postdoctoral researcher at the EcoVision lab at University of Zurich, I collaborate with Jan Dirk Wegner to design deep learning methods for remote sensing and environmental applications. Before joining UZH, I completed my PhD on "Efficient Learning on Large-Scale 3D Point Clouds" at IGN and ENGIE Lab CRIGEN, under the supervision of Loรฏc Landrieu and Bruno Vallet.

You like point clouds โ˜๏ธ ? You like trees ๐ŸŒณ ? You like satellites ๐Ÿ›ฐ๏ธ ? You like me ๐Ÿค—



๐Ÿ“ƒ Publications

๐Ÿ–ผ Poster | ๐ŸŽค Oral

SSL4Eco
SSL4Eco: A Global Seasonal Dataset for Geospatial Foundation Models in Ecology
Paper | Webpage | Code
Elena Plekhanova, Damien Robert, Johannes Dollinger, Emilia Arens, Philipp Brun, Jan Dirk Wegner, Niklaus Zimmermann,
CVPR EarthVision workshop 2025 Poster ๐Ÿ–ผ

This work proposes a spatio-temporal sampling recipe for building pretraining sets for geospatial foundation models targeted for downstream macroecological applications. Simply put, we sample geolocations uniformly across the landmass and sample dates following local, phenology-informed seasons. We create a dataset SSL4Eco following this sampling recipe, on which we pretrain a model following the existing Seasonal Contrast approach. We show that our simple dataset construction recipe significantly impacts the performance on diverse downstream macroecological tasks, compared to other datasets, and pretrained models.



Climplicit
Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks
Paper | Webpage | Code
Johannes Dollinger, Damien Robert, Elena Plekhanova, Lukas Drees, Jan Dirk Wegner,
ICLR Tackling Climate Change with Machine Learning workshop 2025 Poster ๐Ÿ–ผ

Climplicit proposes to learn global, multi-temporal, implicit climatic representations to facilitate the use of climatic data ๐ŸŒฆ for downstream applications with minimal compute, memory, and deep learning expertise requirements ๐Ÿฆ‹.



GSR4B
GSR4B: Biomass Map Super-Resolution with Sentinel-1/2 Guidance
Paper | Webpage | Code
Kaan Karaman, Yuchang Jiang, Damien Robert, Vivien Sainte Fare Garnot, Maria Joรฃo Santos, Jan Dirk Wegner
ISPRS Geospatial Week 2025 Oral ๐ŸŽค

GSR4B proposes a method for producing high-resolution above-ground biomass ๐Ÿชต๐ŸŒณ maps using guided super-resolution. More specifically, we show that it is possible to upsample 100m-resolution AGB maps to 10m resolution with the help of Sentinel-1/2 imagery ๐Ÿ›ฐ. The resulting estimates are more accurate than direct regression solely from Sentinel imagery and less prone to over-estimating low values and under-estimation high values.



Lossy Neural Compression Review
Lossy Neural Compression for Geospatial Analytics: A Review
Paper
Carlos Gomes, Isabelle Wittmann, Damien Robert, Johannes Jakubik, Tim Reichelt, Michele Martone, Stefano Maurogiovanni, Rikard Vinge, Jonas Hurst, Erik Scheurer, Rocco Sedona, Thomas Brunschwiler, Stefan Kesselheim, Matej Batic, Philip Stier, Jan Dirk Wegner, Gabriele Cavallaro, Edzer Pebesma, Michael Marszalek, Miguel A Belenguer-Plomer, Kennedy Adriko, Paolo Fraccaro, Romeo Kienzler, Rania Briq, Sabrina Benassou, Michele Lazzarini, Conrad M Albrecht
IEEE Geoscience and Remote Sensing Magazine 2025

This paper reviews the state of lossy neural compression ๐Ÿค–๐Ÿ—œ๏ธ, with a focus on its application and potential for the manipulation and analysis of Earth Observation data ๐ŸŒ such as satellite imagery ๐Ÿ›ฐ and climate model predictions ๐ŸŒฆ.



SuperCluster
Scalable 3D Panoptic Segmentation as Superpoint Graph Clustering
Damien Robert, Hugo Raguet, Loรฏc Landrieu
Paper | Webpage | Code
3DV 2024 Oral ๐ŸŽค (top 5.3% submissions)

SuperCluster proposes a framework for efficient panoptic segmentation of large-scale point clouds. We formulate the panoptic task as a graph clustering problem. We train a model to predict desirable node and edge attributes to be used as input for a downstream graph clustering algorithm. This allows for training a model with only local supervision, without the need for non-maximum suppression, instance matching, and without any prerequisite on the number of objects in the scene. SuperCluster achieves new SOTA panoptic segmentation on indoor datasets S3DIS Area 5 (50.1 PQ (+7.8)) and ScanNetV2 (58.7 PQ (+25.2)), as well as outdoor datasets KITTI-360 (48.3 PQ) and DALES (61.2 PQ).
๐Ÿฆ‹ 210k param. | โšก Train S3DIS F5 in 4h | ๐Ÿ’พ 20M-point inference on 1 GPU



superpoint transformer
Efficient 3D Semantic Segmentation with Superpoint Transformer
Damien Robert, Hugo Raguet, Loรฏc Landrieu
Paper | Webpage | Code
ICCV 2023 Poster ๐Ÿ–ผ (top 26.8% submissions)

SPT is a superpoint-based transformer ๐Ÿค– architecture that efficiently โšก performs semantic segmentation on large-scale 3D scenes. This method includes a fast algorithm that partitions ๐Ÿงฉ point clouds into a hierarchical superpoint structure, as well as a self-attention mechanism to exploit the relationships between superpoints at multiple scales. We reach SOTA on S3DIS 6-Fold (76.0 mIoU), KITTI-360 Val (63.5 mIoU), and DALES (79.6 mIoU)n with:
๐Ÿฆ‹ 212k param. | โšก Train S3DIS F5 in 3h | โŒš SPG preprocessing รท7



deepviewagg
Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation
Damien Robert, Bruno Vallet, Loรฏc Landrieu
Paper | Webpage | Code | Video
CVPR 2022 Oral ๐ŸŽค and Best Paper finalist ๐ŸŽ‰ (top 0.4% submissions)

An end-to-end multi-view aggregation method for 3D semantic segmentation from images and point clouds. We reach SOTA on S3DIS and KITTI-360 without requiring point cloud colorization, meshing, or depth sensors: just point clouds โ˜, images ๐Ÿ“ธ, and their poses.



๐Ÿ“‘ Short Resume



๐Ÿ… Awards



๐Ÿ–ผ๐ŸŽค Talks & Presentations

๐Ÿ–ผ Poster | ๐ŸŽค Oral



๐Ÿ“š Teaching

  • 05/2024 NeRFs, and Diffusion at University of Zurich (Course Instructor, M2, 5.5 hours)
  • 01/2023 Deep Learning for Remote Sensing at ENSG (Course Instructor, M2, 13 hours)
  • 06/2022 3D Deep Learning for Remote Sensing at ISPRS 2022 (Tutorial Instructor, 1 day)
  • 05/2022 3D Deep Learning, Torch-Points3D & DeepViewAgg at ENGIE Lab CRIGEN (Tutorial Instructor, 1 day)
  • 01/2022 Deep Learning for Remote Sensing at ENSG (Course Instructor, M2, 9 hours)
  • 11/2020 Deep Learning for Computer Vision at Ecole Polytechnique (Teaching Assistant, M1, 12 hours)


๐Ÿ  Affiliations