Posts by Collection

publications

A Survey on Deep Domain Adaptation for LiDAR Perception

Published in IEEE Intelligent Vehicles Symposium (IV) Workshops, 2021

This paper presents a comprehensive review of recent progress in domain adaptation methods and formulates interesting research questions specifically targeted towards LiDAR perception.

Download here

Semi-Local Convolutions for LiDAR Scan Processing

Published in Advances in Neural Information Processing Systems (NeurIPS) Workshops, 2021

This paper proposes semi local convolution (SLC), a convolution layer with reduced amount of weight-sharing along the vertical dimension.

Download here

Point Cloud Generation with Continuous Conditioning

Published in International Conference on Artificial Intelligence and Statistics (AISTATS), 2022

This paper proposes a novel generative adversarial network (GAN) setup that generates 3D point cloud shapes conditioned on a continuous parameter.

Download here

A Realism Metric for Generated LiDAR Point Clouds

Published in International Journal of Computer Vision (IJCV), 2022

This paper presents a novel metric to quantify the realism of LiDAR point clouds. We confirm that our metric provides an indication for the downstream segmentation performance.

Download here