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

We present a method for teaching machines to understand and model theunderlying spatial common sense of diverse human-object interactions in 3D in aself-supervised way. This is a challenging task, as there exist specificmanifolds of the interactions that can be considered human-like and natural,but the human pose and the geometry of objects can vary even for similarinteractions. Such diversity makes the annotating task of 3D interactionsdifficult and hard to scale, which limits the potential to reason about that ina supervised way. One way of learning the 3D spatial relationship betweenhumans and objects during interaction is by showing multiple 2D images capturedfrom different viewpoints when humans interact with the same type of objects.The core idea of our method is to leverage a generative model that produceshigh-quality 2D images from an arbitrary text prompt input as an "unbounded"data generator with effective controllability and view diversity. Despite itsimperfection of the image quality over real images, we demonstrate that thesynthesized images are sufficient to learn the 3D human-object spatialrelations. We present multiple strategies to leverage the synthesized images,including (1) the first method to leverage a generative image model for 3Dhuman-object spatial relation learning; (2) a framework to reason about the 3Dspatial relations from inconsistent 2D cues in a self-supervised manner via 3Doccupancy reasoning with pose canonicalization; (3) semantic clustering todisambiguate different types of interactions with the same object types; and(4) a novel metric to assess the quality of 3D spatial learning of interaction.

CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images