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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Tracking non-rigidly deforming scenes using range sensors has numerousapplications including computer vision, AR/VR, and robotics. However, due toocclusions and physical limitations of range sensors, existing methods onlyhandle the visible surface, thus causing discontinuities and incompleteness inthe motion field. To this end, we introduce 4DComplete, a novel data-drivenapproach that estimates the non-rigid motion for the unobserved geometry.4DComplete takes as input a partial shape and motion observation, extracts 4Dtime-space embedding, and jointly infers the missing geometry and motion fieldusing a sparse fully-convolutional network. For network training, weconstructed a large-scale synthetic dataset called DeformingThings4D, whichconsists of 1972 animation sequences spanning 31 different animals or humanoidcategories with dense 4D annotation. Experiments show that 4DComplete 1)reconstructs high-resolution volumetric shape and motion field from a partialobservation, 2) learns an entangled 4D feature representation that benefitsboth shape and motion estimation, 3) yields more accurate and naturaldeformation than classic non-rigid priors such as As-Rigid-As-Possible (ARAP)deformation, and 4) generalizes well to unseen objects in real-world sequences.

4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface