International audienceScene understanding has made tremendous progress over the past few years, as data acquisition systems are now providing an increasing amount of data of various modalities (point cloud, depth, RGB...). However, this improvement comes at a large cost on computation resources and data annotation requirements. To analyze geometric information and images jointly, many approaches rely on both a 2D loss and 3D loss, requiring not only 2D per pixel-labels but also 3D per-point labels. However, obtaining a 3D groundtruth is challenging, time-consuming and error-prone. In this paper, we show that image segmentation can benefit from 3D geometric information without requiring a 3D groundtruth, by training the geometric feature ext...
International audienceConventional 2D Convolutional Neural Networks (CNN) extract features from an i...
Geometry Meets Deep Learning Workshop, ICCV 2019International audienceFusion of 2D images and 3D poi...
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in ...
Scene understanding has made tremendous progress over the past few years, as data acquisition system...
The semantic segmentation of 3D shapes with a high-density of vertices could be impractical due to l...
Deep learning has achieved tremendous progress and success in processing images and natural language...
Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) d...
To endow machines with the ability to perceive the real-world in a three dimensional representation ...
In this thesis, we first present a unified look to several well known 3D feature representations, ra...
Semantic augmentation of 3D point clouds is a challenging problem with numerous real-world applicati...
In spite of the good performance of convolutional neural network (CNN) and graph neural network (GNN...
This thesis contributes to the emerging field of 3D scene understanding. That is, given a 3D scene r...
Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for train...
Understanding 3D object structure from a single image is an important but difficult task in computer...
Part segmentation is the task of semantic segmentation applied on objects and carries a wide range o...
International audienceConventional 2D Convolutional Neural Networks (CNN) extract features from an i...
Geometry Meets Deep Learning Workshop, ICCV 2019International audienceFusion of 2D images and 3D poi...
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in ...
Scene understanding has made tremendous progress over the past few years, as data acquisition system...
The semantic segmentation of 3D shapes with a high-density of vertices could be impractical due to l...
Deep learning has achieved tremendous progress and success in processing images and natural language...
Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) d...
To endow machines with the ability to perceive the real-world in a three dimensional representation ...
In this thesis, we first present a unified look to several well known 3D feature representations, ra...
Semantic augmentation of 3D point clouds is a challenging problem with numerous real-world applicati...
In spite of the good performance of convolutional neural network (CNN) and graph neural network (GNN...
This thesis contributes to the emerging field of 3D scene understanding. That is, given a 3D scene r...
Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for train...
Understanding 3D object structure from a single image is an important but difficult task in computer...
Part segmentation is the task of semantic segmentation applied on objects and carries a wide range o...
International audienceConventional 2D Convolutional Neural Networks (CNN) extract features from an i...
Geometry Meets Deep Learning Workshop, ICCV 2019International audienceFusion of 2D images and 3D poi...
A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in ...