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

Various heuristic objectives for modeling hand-object interaction have beenproposed in past work. However, due to the lack of a cohesive framework, theseobjectives often possess a narrow scope of applicability and are limited bytheir efficiency or accuracy. In this paper, we propose HandyPriors, a unifiedand general pipeline for pose estimation in human-object interaction scenes byleveraging recent advances in differentiable physics and rendering. Ourapproach employs rendering priors to align with input images and segmentationmasks along with physics priors to mitigate penetration and relative-slidingacross frames. Furthermore, we present two alternatives for hand and objectpose estimation. The optimization-based pose estimation achieves higheraccuracy, while the filtering-based tracking, which utilizes the differentiablepriors as dynamics and observation models, executes faster. We demonstrate thatHandyPriors attains comparable or superior results in the pose estimation task,and that the differentiable physics module can predict contact information forpose refinement. We also show that our approach generalizes to perceptiontasks, including robotic hand manipulation and human-object pose estimation inthe wild.

HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors