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

Perception sensor models are essential elements of automotive simulationenvironments; they also serve as powerful tools for creating synthetic datasetsto train deep learning-based perception models. Developing realistic perceptionsensor models poses a significant challenge due to the large gap betweensimulated sensor data and real-world sensor outputs, known as the sim-to-realgap. To address this problem, learning-based models have emerged as promisingsolutions in recent years, with unparalleled potential to map low-fidelitysimulated sensor data into highly realistic outputs. Motivated by thispotential, this paper focuses on sim-to-real mapping of Lidar point clouds, awidely used perception sensor in automated driving systems. We introduce anovel Contrastive-Learning-based Sim-to-Real mapping framework, namely CLS2R,inspired by the recent advancements in image-to-image translation techniques.The proposed CLS2R framework employs a lossless representation of Lidar pointclouds, considering all essential Lidar attributes such as depth, reflectance,and raydrop. We extensively evaluate the proposed framework, comparing it withstate-of-the-art image-to-image translation methods using a diverse range ofmetrics to assess realness, faithfulness, and the impact on the performance ofa downstream task. Our results show that CLS2R demonstrates superiorperformance across nearly all metrics. Source code is available athttps://github.com/hamedhaghighi/CLS2R.git.

Contrastive Learning-Based Framework for Sim-to-Real Mapping of Lidar Point Clouds in Autonomous Driving Systems