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

3D point cloud semantic segmentation has a wide range of applications.Recently, weakly supervised point cloud segmentation methods have beenproposed, aiming to alleviate the expensive and laborious manual annotationprocess by leveraging scene-level labels. However, these methods have noteffectively exploited the rich geometric information (such as shape and scale)and appearance information (such as color and texture) present in RGB-D scans.Furthermore, current approaches fail to fully leverage the point affinity thatcan be inferred from the feature extraction network, which is crucial forlearning from weak scene-level labels. Additionally, previous work overlooksthe detrimental effects of the long-tailed distribution of point cloud data inweakly supervised 3D semantic segmentation. To this end, this paper proposes asimple yet effective scene-level weakly supervised point cloud segmentationmethod with a newly introduced multi-modality point affinity inference module.The point affinity proposed in this paper is characterized by features frommultiple modalities (e.g., point cloud and RGB), and is further refined bynormalizing the classifier weights to alleviate the detrimental effects oflong-tailed distribution without the need of the prior of categorydistribution. Extensive experiments on the ScanNet and S3DIS benchmarks verifythe effectiveness of our proposed method, which outperforms thestate-of-the-art by ~4% to ~6% mIoU. Codes are released athttps://github.com/Sunny599/AAAI24-3DWSSG-MMA.

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation