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 Deep Shape-from-Template (DeepSfT), a novel Deep Neural Network(DNN) method for solving real-time automatic registration and 3D reconstructionof a deformable object viewed in a single monocular image.DeepSfT advances thestate-of-the-art in various aspects. Compared to existing DNN SfT methods, itis the first fully convolutional real-time approach that handles an arbitraryobject geometry, topology and surface representation. It also does not requireground truth registration with real data and scales well to very complex objectmodels with large numbers of elements. Compared to previous non-DNN SfTmethods, it does not involve numerical optimization at run-time, and is adense, wide-baseline solution that does not demand, and does not suffer from,feature-based matching. It is able to process a single image with significantdeformation and viewpoint changes, and handles well the core challenges ofocclusions, weak texture and blur. DeepSfT is based on residual encoder-decoderstructures and refining blocks. It is trained end-to-end with a novelcombination of supervised learning from simulated renderings of the objectmodel and semi-supervised automatic fine-tuning using real data captured with astandard RGB-D camera. The cameras used for fine-tuning and run-time can bedifferent, making DeepSfT practical for real-world use. We show that DeepSfTsignificantly outperforms state-of-the-art wide-baseline approaches fornon-trivial templates, with quantitative and qualitative evaluation.

Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image