360deg from a Single Camera: A Few-Shot Approach for LiDAR Segmentation

Laurenz Reichardt, Nikolas Ebert, Oliver Wasenm├╝ller; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 1075-1083

Abstract


Deep learning applications on LiDAR data suffer from a strong domain gap when applied to different sensors or tasks. In order for these methods to obtain similar accuracy on different data in comparison to values reported on public benchmarks, a large scale annotated dataset is necessary. However, in practical applications labeled data is costly and time consuming to obtain. Such factors have triggered various research in label-efficient methods, but a large gap remains to their fully-supervised counterparts. Thus, we propose ImageTo360, an effective and streamlined few-shot approach to label-efficient LiDAR segmentation. Our method utilizes an image teacher network to generate semantic predictions for LiDAR data within a single camera view. The teacher is used to pretrain the LiDAR segmentation student network, prior to optional fine-tuning on 360deg data. Our method is implemented in a modular manner on the point level and as such is generalizable to different architectures. We improve over the current state-of-the-art results for label-efficient methods and even surpass some traditional fully-supervised segmentation networks.

Related Material


[pdf]
[bibtex]
@InProceedings{Reichardt_2023_ICCV, author = {Reichardt, Laurenz and Ebert, Nikolas and Wasenm\"uller, Oliver}, title = {360deg from a Single Camera: A Few-Shot Approach for LiDAR Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {1075-1083} }