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

In this technical report, we present our solution, named UniOCC, for theVision-Centric 3D occupancy prediction track in the nuScenes Open DatasetChallenge at CVPR 2023. Existing methods for occupancy prediction primarilyfocus on optimizing projected features on 3D volume space using 3D occupancylabels. However, the generation process of these labels is complex andexpensive (relying on 3D semantic annotations), and limited by voxelresolution, they cannot provide fine-grained spatial semantics. To address thislimitation, we propose a novel Unifying Occupancy (UniOcc) prediction method,explicitly imposing spatial geometry constraint and complementing fine-grainedsemantic supervision through volume ray rendering. Our method significantlyenhances model performance and demonstrates promising potential in reducinghuman annotation costs. Given the laborious nature of annotating 3D occupancy,we further introduce a Depth-aware Teacher Student (DTS) framework to enhanceprediction accuracy using unlabeled data. Our solution achieves 51.27\% mIoU onthe official leaderboard with single model, placing 3rd in this challenge.

UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering