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 human generation is increasingly significant in various applications.However, the direct use of 2D generative methods in 3D generation often resultsin significant loss of local details, while methods that reconstruct geometryfrom generated images struggle with global view consistency. In this work, weintroduce Joint2Human, a novel method that leverages 2D diffusion models togenerate detailed 3D human geometry directly, ensuring both global structureand local details. To achieve this, we employ the Fourier occupancy field (FOF)representation, enabling the direct production of 3D shapes as preliminaryresults using 2D generative models. With the proposed high-frequency enhancerand the multi-view recarving strategy, our method can seamlessly integrate thedetails from different views into a uniform global shape.To better utilize the3D human prior and enhance control over the generated geometry, we introduce acompact spherical embedding of 3D joints. This allows for effective applicationof pose guidance during the generation process. Additionally, our method iscapable of generating 3D humans guided by textual inputs. Our experimentalresults demonstrate the capability of our method to ensure global structure,local details, high resolution, and low computational cost, simultaneously.More results and code can be found on our project page athttp://cic.tju.edu.cn/faculty/likun/projects/Joint2Human.

Joint2Human: High-quality 3D Human Generation via Compact Spherical Embedding of 3D Joints