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

Understanding the inherent human knowledge in interacting with a givenenvironment (e.g., affordance) is essential for improving AI to better assisthumans. While existing approaches primarily focus on human-object contactsduring interactions, such affordance representation cannot fully address otherimportant aspects of human-object interactions (HOIs), i.e., patterns ofrelative positions and orientations. In this paper, we introduce a novelaffordance representation, named Comprehensive Affordance (ComA). Given a 3Dobject mesh, ComA models the distribution of relative orientation and proximityof vertices in interacting human meshes, capturing plausible patterns ofcontact, relative orientations, and spatial relationships. To construct thedistribution, we present a novel pipeline that synthesizes diverse andrealistic 3D HOI samples given any 3D object mesh. The pipeline leverages apre-trained 2D inpainting diffusion model to generate HOI images from objectrenderings and lifts them into 3D. To avoid the generation of falseaffordances, we propose a new inpainting framework, Adaptive Mask Inpainting.Since ComA is built on synthetic samples, it can extend to any object in anunbounded manner. Through extensive experiments, we demonstrate that ComAoutperforms competitors that rely on human annotations in modelingcontact-based affordance. Importantly, we also showcase the potential of ComAto reconstruct human-object interactions in 3D through an optimizationframework, highlighting its advantage in incorporating both contact andnon-contact properties.

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models