English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

LiDAR sensors can provide dependable 3D spatial information at a lowfrequency (around 10Hz) and have been widely applied in the field of autonomousdriving and UAV. However, the camera with a higher frequency (around 20Hz) hasto be decreased so as to match with LiDAR in a multi-sensor system. In thispaper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increasethe frequency of LiDAR sensors. PLIN can generate temporally and spatiallyhigh-quality point cloud sequences to match the high frequency of cameras. Toachieve this goal, we design a coarse interpolation stage guided by consecutivesparse depth maps and motion relationship. We also propose a refinedinterpolation stage guided by the realistic scene. Using this coarse-to-finecascade structure, our method can progressively perceive multi-modalinformation and generate accurate intermediate point clouds. To the best of ourknowledge, this is the first deep framework for Pseudo-LiDAR point cloudinterpolation, which shows appealing applications in navigation systemsequipped with LiDAR and cameras. Experimental results demonstrate that PLINachieves promising performance on the KITTI dataset, significantlyoutperforming the traditional interpolation method and the state-of-the-artvideo interpolation technique.

PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation