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

Autonomous driving system development is critically dependent on the abilityto replay complex and diverse traffic scenarios in simulation. In suchscenarios, the ability to accurately simulate the vehicle sensors such ascameras, lidar or radar is essential. However, current sensor simulatorsleverage gaming engines such as Unreal or Unity, requiring manual creation ofenvironments, objects and material properties. Such approaches have limitedscalability and fail to produce realistic approximations of camera, lidar, andradar data without significant additional work.  In this paper, we present a simple yet effective approach to generaterealistic scenario sensor data, based only on a limited amount of lidar andcamera data collected by an autonomous vehicle. Our approach usestexture-mapped surfels to efficiently reconstruct the scene from an initialvehicle pass or set of passes, preserving rich information about object 3Dgeometry and appearance, as well as the scene conditions. We then leverage aSurfelGAN network to reconstruct realistic camera images for novel positionsand orientations of the self-driving vehicle and moving objects in the scene.We demonstrate our approach on the Waymo Open Dataset and show that it cansynthesize realistic camera data for simulated scenarios. We also create anovel dataset that contains cases in which two self-driving vehicles observethe same scene at the same time. We use this dataset to provide additionalevaluation and demonstrate the usefulness of our SurfelGAN model.

SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving