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

Zero-shot neural scene segmentation, which reconstructs 3D neuralsegmentation field without manual annotations, serves as an effective way forscene understanding. However, existing models, especially the efficient 3DGaussian-based methods, struggle to produce compact segmentation results. Thisissue stems primarily from their redundant learnable attributes assigned onindividual Gaussians, leading to a lack of robustness against the3D-inconsistencies in zero-shot generated raw labels. To address this problem,our work, named Compact Segmented 3D Gaussians (CoSegGaussians), proposes theFeature Unprojection and Fusion module as the segmentation field, whichutilizes a shallow decoder generalizable for all Gaussians based on high-levelfeatures. Specifically, leveraging the learned Gaussian geometric parameters,semantic-aware image-based features are introduced into the scene via ourunprojection technique. The lifted features, together with spatial information,are fed into the multi-scale aggregation decoder to generate segmentationidentities for all Gaussians. Furthermore, we design CoSeg Loss to boost modelrobustness against 3D-inconsistent noises. Experimental results show that ourmodel surpasses baselines on zero-shot semantic segmentation task, improving by~10% mIoU over the best baseline. Code and more results will be available athttps://David-Dou.github.io/CoSegGaussians.

Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation