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

Understanding what objects could furnish for humans-namely, learning objectaffordance-is the crux to bridge perception and action. In the visioncommunity, prior work primarily focuses on learning object affordance withdense (e.g., at a per-pixel level) supervision. In stark contrast, we humanslearn the object affordance without dense labels. As such, the fundamentalquestion to devise a computational model is: What is the natural way to learnthe object affordance from visual appearance and geometry with humanlike sparsesupervision? In this work, we present a new task of part-level affordancediscovery (PartAfford): Given only the affordance labels per object, themachine is tasked to (i) decompose 3D shapes into parts and (ii) discover howeach part of the object corresponds to a certain affordance category. Wepropose a novel learning framework for PartAfford, which discovers part-levelrepresentations by leveraging only the affordance set supervision and geometricprimitive regularization, without dense supervision. The proposed approachconsists of two main components: (i) an abstraction encoder with slot attentionfor unsupervised clustering and abstraction, and (ii) an affordance decoderwith branches for part reconstruction, affordance prediction, and cuboidalprimitive regularization. To learn and evaluate PartAfford, we construct apart-level, cross-category 3D object affordance dataset, annotated with 24affordance categories shared among >25, 000 objects. We demonstrate that ourmethod enables both the abstraction of 3D objects and part-level affordancediscovery, with generalizability to difficult and cross-category examples.Further ablations reveal the contribution of each component.

PartAfford: Part-level Affordance Discovery from 3D Objects