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

Reconstructing hand-held objects from a single RGB image is an important andchallenging problem. Existing works utilizing Signed Distance Fields (SDF)reveal limitations in comprehensively capturing the complex hand-objectinteractions, since SDF is only reliable within the proximity of the target,and hence, infeasible to simultaneously encode local hand and object cues. Toaddress this issue, we propose DDF-HO, a novel approach leveraging DirectedDistance Field (DDF) as the shape representation. Unlike SDF, DDF maps a ray in3D space, consisting of an origin and a direction, to corresponding DDF values,including a binary visibility signal determining whether the ray intersects theobjects and a distance value measuring the distance from origin to target inthe given direction. We randomly sample multiple rays and collect local toglobal geometric features for them by introducing a novel 2D ray-based featureaggregation scheme and a 3D intersection-aware hand pose embedding, combining2D-3D features to model hand-object interactions. Extensive experiments onsynthetic and real-world datasets demonstrate that DDF-HO consistentlyoutperforms all baseline methods by a large margin, especially under ChamferDistance, with about 80% leap forward. Codes are available athttps://github.com/ZhangCYG/DDFHO.

DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field