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/

Zendy Plus

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

Zendy Tools

Zendy Open

Monocular dense 3D reconstruction of deformable objects is a hard ill-posedproblem in computer vision. Current techniques either require densecorrespondences and rely on motion and deformation cues, or assume a highlyaccurate reconstruction (referred to as a template) of at least a single framegiven in advance and operate in the manner of non-rigid tracking. Accuratecomputation of dense point tracks often requires multiple frames and might becomputationally expensive. Availability of a template is a very strong priorwhich restricts system operation to a pre-defined environment and scenarios. Inthis work, we propose a new hybrid approach for monocular non-rigidreconstruction which we call Hybrid Deformation Model Network (HDM-Net). In ourapproach, deformation model is learned by a deep neural network, with acombination of domain-specific loss functions. We train the network withmultiple states of a non-rigidly deforming structure with a known shape atrest. HDM-Net learns different reconstruction cues including texture-dependentsurface deformations, shading and contours. We show generalisability of HDM-Netto states not presented in the training dataset, with unseen textures and undernew illumination conditions. Experiments with noisy data and a comparison withother methods demonstrate robustness and accuracy of the proposed approach andsuggest possible application scenarios of the new technique in interventionaldiagnostics and augmented reality.

HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model