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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In recent years, 3D models have been utilized in many applications, such asauto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D modeldata does not meet its practical demands. Thus, generating high-quality 3Dmodels efficiently from textual descriptions is a promising but challenging wayto solve this problem. In this paper, inspired by the ability of human beingsto complement visual information details from ambiguous descriptions based ontheir own experience, we propose a novel text-3D generation model (T2TD), whichintroduces the related shapes or textual information as the prior knowledge toimprove the performance of the 3D generation model. In this process, we firstintroduce the text-3D knowledge graph to save the relationship between 3Dmodels and textual semantic information, which can provide the related shapesto guide the target 3D model generation. Second, we integrate an effectivecausal inference model to select useful feature information from these relatedshapes, which removes the unrelated shape information and only maintainsfeature information that is strongly relevant to the textual description.Meanwhile, to effectively integrate multi-modal prior knowledge into textualinformation, we adopt a novel multi-layer transformer structure toprogressively fuse related shape and textual information, which can effectivelycompensate for the lack of structural information in the text and enhance thefinal performance of the 3D generation model. The final experimental resultsdemonstrate that our approach significantly improves 3D model generationquality and outperforms the SOTA methods on the text2shape datasets.

T2TD: Text-3D Generation Model based on Prior Knowledge Guidance