3 papers
cs.CV2023
Living in a Material World: Learning Material Properties from Full-Waveform Flash Lidar Data for Semantic Segmentation
Andrej Janda, Pierre Merriaux, Pierre Olivier +1
Advances in lidar technology have made the collection of 3D point clouds fast and easy. While most lidar sensors return per-point intensity (or reflectance) values along with range…
cs.CV2023
Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
Andrej Janda, Brandon Wagstaff, Edwin G. Ng +1
Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation…
cs.CV2022
Self-Supervised Pre-training of 3D Point Cloud Networks with Image Data
Andrej Janda, Brandon Wagstaff, Edwin G. Ng +1
Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation t…