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 to reconstruct a dense spatio-temporal depth map of anon-rigidly deformable object directly from a video sequence. The estimation ofdepth is performed locally on spatio-temporal patches of the video, and thenthe full depth video of the entire shape is recovered by combining themtogether. Since the geometric complexity of a local spatio-temporal patch of adeforming non-rigid object is often simple enough to be faithfully representedwith a parametric model, we artificially generate a database of small deformingrectangular meshes rendered with different material properties and lightconditions, along with their corresponding depth videos, and use such data totrain a convolutional neural network. We tested our method on both syntheticand Kinect data and experimentally observed that the reconstruction error issignificantly lower than the one obtained using other approaches likeconventional non-rigid structure from motion.

Learning non-rigid surface reconstruction from spatio-temporal image patches