-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Bin and Pfreundschuh, Patrick and Siegwart, Roland and Hutter, Marco and Moghadam, Peyman and Patil, Vaishakh}, title = {TULIP: Transformer for Upsampling of LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15354-15364} }
TULIP: Transformer for Upsampling of LiDAR Point Clouds
Abstract
LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution problem in 2D image space. Although their methods can generate high-resolution range images with fine-grained details the resulting 3D point clouds often blur out details and predict invalid points. In this paper we propose TULIP a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input. We also follow a range image-based approach but specifically modify the patch and window geometries of a Swin-Transformer-based network to better fit the characteristics of range images. We conducted several experiments on three public real-world and simulated datasets. TULIP outperforms state-of-the-art methods in all relevant metrics and generates robust and more realistic point clouds than prior works.
Related Material