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

Occupancy prediction reconstructs 3D structures of surrounding environments.It provides detailed information for autonomous driving planning andnavigation. However, most existing methods heavily rely on the LiDAR pointclouds to generate occupancy ground truth, which is not available in thevision-based system. In this paper, we propose an OccNeRF method for trainingoccupancy networks without 3D supervision. Different from previous works whichconsider a bounded scene, we parameterize the reconstructed occupancy fieldsand reorganize the sampling strategy to align with the cameras' infiniteperceptive range. The neural rendering is adopted to convert occupancy fieldsto multi-camera depth maps, supervised by multi-frame photometric consistency.Moreover, for semantic occupancy prediction, we design several strategies topolish the prompts and filter the outputs of a pretrained open-vocabulary 2Dsegmentation model. Extensive experiments for both self-supervised depthestimation and 3D occupancy prediction tasks on nuScenes and SemanticKITTIdatasets demonstrate the effectiveness of our method.

OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments