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/

Zendy Plus

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

Zendy Tools

Zendy Open

3D point cloud semantic segmentation is fundamental for autonomous driving.Most approaches in the literature neglect an important aspect, i.e., how todeal with domain shift when handling dynamic scenes. This can significantlyhinder the navigation capabilities of self-driving vehicles. This paperadvances the state of the art in this research field. Our first contributionconsists in analysing a new unexplored scenario in point cloud segmentation,namely Source-Free Online Unsupervised Domain Adaptation (SF-OUDA). Weexperimentally show that state-of-the-art methods have a rather limited abilityto adapt pre-trained deep network models to unseen domains in an online manner.Our second contribution is an approach that relies on adaptive self-trainingand geometric-feature propagation to adapt a pre-trained source model onlinewithout requiring either source data or target labels. Our third contributionis to study SF-OUDA in a challenging setup where source data is synthetic andtarget data is point clouds captured in the real world. We use the recentSynLiDAR dataset as a synthetic source and introduce two new synthetic (source)datasets, which can stimulate future synthetic-to-real autonomous drivingresearch. Our experiments show the effectiveness of our segmentation approachon thousands of real-world point clouds. Code and synthetic datasets areavailable at https://github.com/saltoricristiano/gipso-sfouda.

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation