As a PhD candidate at IGN—the French Mapping Agency 🗺—in the machine
STRUDEL (LASTIG lab, IGN-ENSG, Univ. Gustave Eiffel),
and in the CSAI team at ENGIE Lab CRIGEN, I design deep learning methods for multimodal,
multi-task learning on large-scale point clouds. Specifically, my recent research involves
computer vision on 3D point clouds and 2D images in the wild.
You like point clouds ☁ ? You like images 📸 ? You like me 😊.
- Loïc Landrieu (Univ. Gustave Eiffel, IGN-ENSG, LASTIG, STRUDEL, Saint-Mandé, France)
- Bruno Vallet (Univ. Gustave Eiffel, IGN-ENSG, LASTIG, ACTE, Saint-Mandé, France)
Publications 📄¶🖼 Poster | 🎤 Oral
Damien Robert, Bruno Vallet, Loïc Landrieu
Paper | Webpage | Code | Video
CVPR 2022 Oral 🖼🎤
We present an end-to-end deep 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 ☁, images 📸, and their poses.
- [2020 - Now] PhD student on "Multimodal, multi-task learning on large-scale 3D point clouds" supervised by Loïc Landrieu and Bruno Vallet.
- [Jul 2022] International Computer Vision Summer School, in Sicily.
- [Oct 2017] CNRS AI Fall School, Multi-disciplinary course for AI students and researchers.
- [2011 - 2015] Master of Science at Ecole Centrale de Lyon.
Talks¶🖼 Poster | 🎤 Oral | 🎓 Tutorial
- 🖼 [Jul 2022] ICVSS DeepViewAgg
- 🎤 [Jun 2022] CVPR DeepViewAgg
- 🎤 [Jun 2022] Ecole des Ponts, IMAGINE lab DeepViewAgg
- 🎓 [Jun 2022] ISPRS 3D Deep Learning for Remote Sensing
- 🖼 [Jun 2022] ISPRS DeepViewAgg
- 🎓 [May 2022] ENGIE CRIGEN lab 3D Deep Learning, Torch-Points3D & DeepViewAgg
- 🎤 [May 2022] Ecole Polytechnique, LIX lab DeepViewAgg
- 🎤 [Apr 2022] AI4GEO project seminar DeepViewAgg
- 🖼 [Mar 2022] IGN-ENSG Research Days DeepViewAgg
- 🎤 [Jan 2022] GDR ISIS seminar DeepViewAgg
- 🖼 [May 2021] IGN-ENSG Research Days DeepViewAgg
- [Jan 2022] ENSG-IGN Course Instructor, M2, 9 hours Deep learning for Remote Sensing
- [Nov 2020] Ecole Polytechnique Teaching Assistant, M1, 12 hours Computer vision