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

Precise 3D environmental mapping is pivotal in robotics. Existing methodsoften rely on predefined concepts during training or are time-intensive whengenerating semantic maps. This paper presents Open-Fusion, a groundbreakingapproach for real-time open-vocabulary 3D mapping and queryable scenerepresentation using RGB-D data. Open-Fusion harnesses the power of apre-trained vision-language foundation model (VLFM) for open-set semanticcomprehension and employs the Truncated Signed Distance Function (TSDF) forswift 3D scene reconstruction. By leveraging the VLFM, we extract region-basedembeddings and their associated confidence maps. These are then integrated with3D knowledge from TSDF using an enhanced Hungarian-based feature-matchingmechanism. Notably, Open-Fusion delivers outstanding annotation-free 3Dsegmentation for open-vocabulary without necessitating additional 3D training.Benchmark tests on the ScanNet dataset against leading zero-shot methodshighlight Open-Fusion's superiority. Furthermore, it seamlessly combines thestrengths of region-based VLFM and TSDF, facilitating real-time 3D scenecomprehension that includes object concepts and open-world semantics. Weencourage the readers to view the demos on our project page:https://uark-aicv.github.io/OpenFusion

Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation