Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion

Kamil Adamczewski, Christos Sakaridis, Vaishakh Patil, Luc Van Gool
Proceedings of The 6th Conference on Robot Learning, PMLR 205:561-570, 2023.

Abstract

Lidar is a vital sensor for estimating the depth of a scene. Typical spinning lidars emit pulses arranged in several horizontal lines and the monetary cost of the sensor increases with the number of these lines. In this work, we present the new problem of optimizing the positioning of lidar lines to find the most effective configuration for the depth completion task. We propose a solution to reduce the number of lines while retaining the up-to-the-mark quality of depth completion. Our method consists of two components, (1) line selection based on the marginal contribution of a line computed via the Shapley value and (2) incorporating line position spread to take into account its need to arrive at image-wide depth completion. Spatially-aware Shapley values (SaS) succeed in selecting line subsets that yield a depth accuracy comparable to the full lidar input while using just half of the lines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-adamczewski23a, title = {Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion}, author = {Adamczewski, Kamil and Sakaridis, Christos and Patil, Vaishakh and Gool, Luc Van}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {561--570}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/adamczewski23a/adamczewski23a.pdf}, url = {https://proceedings.mlr.press/v205/adamczewski23a.html}, abstract = {Lidar is a vital sensor for estimating the depth of a scene. Typical spinning lidars emit pulses arranged in several horizontal lines and the monetary cost of the sensor increases with the number of these lines. In this work, we present the new problem of optimizing the positioning of lidar lines to find the most effective configuration for the depth completion task. We propose a solution to reduce the number of lines while retaining the up-to-the-mark quality of depth completion. Our method consists of two components, (1) line selection based on the marginal contribution of a line computed via the Shapley value and (2) incorporating line position spread to take into account its need to arrive at image-wide depth completion. Spatially-aware Shapley values (SaS) succeed in selecting line subsets that yield a depth accuracy comparable to the full lidar input while using just half of the lines.} }
Endnote
%0 Conference Paper %T Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion %A Kamil Adamczewski %A Christos Sakaridis %A Vaishakh Patil %A Luc Van Gool %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-adamczewski23a %I PMLR %P 561--570 %U https://proceedings.mlr.press/v205/adamczewski23a.html %V 205 %X Lidar is a vital sensor for estimating the depth of a scene. Typical spinning lidars emit pulses arranged in several horizontal lines and the monetary cost of the sensor increases with the number of these lines. In this work, we present the new problem of optimizing the positioning of lidar lines to find the most effective configuration for the depth completion task. We propose a solution to reduce the number of lines while retaining the up-to-the-mark quality of depth completion. Our method consists of two components, (1) line selection based on the marginal contribution of a line computed via the Shapley value and (2) incorporating line position spread to take into account its need to arrive at image-wide depth completion. Spatially-aware Shapley values (SaS) succeed in selecting line subsets that yield a depth accuracy comparable to the full lidar input while using just half of the lines.
APA
Adamczewski, K., Sakaridis, C., Patil, V. & Gool, L.V.. (2023). Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:561-570 Available from https://proceedings.mlr.press/v205/adamczewski23a.html.

Related Material