International audienceWe propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds as interconnected object parts can be efficiently captured by a structure called superpoint graph (SPG). Our framework sets a new state of the art for segmenting outdoor LiDAR scans (+11.9 and +8.8 mIoU points for both Semantic3D test sets [13]), as well as indoor scans (+12.4 mIoU points for the S3DIS dataset [2]). This is a french translation of the article [25].Nous proposons dans cet article une méthode pour la seg-mentation sémantique de nuages de millions de points basée sur l'apprentissage profond. Nous introduisons ...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Recent advances in Light Detection and Ranging (LiDAR) sensors have led to an increasing amount of l...
Machine learning has made phenomenal progress in the past decades. This work has a focus on the chal...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
peer reviewedThis article describes a complete unsupervised system for the segmentation of massive 3...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Semantic segmentation of point clouds is indispensable for 3D scene understanding. Point clouds have...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Recent advances in Light Detection and Ranging (LiDAR) sensors have led to an increasing amount of l...
Machine learning has made phenomenal progress in the past decades. This work has a focus on the chal...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
International audienceWe propose a novel deep learning-based framework to tackle the challenge of se...
peer reviewedThis article describes a complete unsupervised system for the segmentation of massive 3...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Semantic segmentation of large-scale outdoor 3D LiDAR point clouds becomes essential to understand t...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Semantic segmentation of point clouds is indispensable for 3D scene understanding. Point clouds have...
Terrestrial laser scanners enable to acquire a lot of datas while being fast and easy to get. But th...
Recent advances in Light Detection and Ranging (LiDAR) sensors have led to an increasing amount of l...
Machine learning has made phenomenal progress in the past decades. This work has a focus on the chal...