Current LiDAR systems are limited in their ability to capture dense 3D point clouds. To overcome this challenge, deep learning-based depth completion algorithms have been developed to inpaint missing depth guided by an RGB image. However, these methods fail for low sampling rates. Here, we propose an adaptive sampling scheme for LiDAR systems that demonstrates state-of-the-art performance for depth completion at low sampling rates. Our system is fully differentiable, allowing the sparse depth sampling and the depth inpainting components to be trained end-to-end with an upstream task.
|Original language||English (US)|
|Title of host publication||2020 IEEE International Conference on Computational Photography (ICCP)|
|State||Published - Jun 2 2020|
Bibliographical noteKAUST Repository Item: Exported on 2022-06-30
Acknowledgements: A.W.B. and D.B.L. are supported by a Stanford Graduate Fellowship in Science and Engineering. This project was supported by a Terman Faculty Fellowship, a Sloan Fellowship, a NSF CAREER Award (IIS 1553333), the DARPA REVEAL program, the ARO (ECASE-Army Award W911NF-19-1-0120), and by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant
This publication acknowledges KAUST support, but has no KAUST affiliated authors.