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

The underlying dynamics and patterns of 3D surface meshes deforming over timecan be discovered by unsupervised learning, especially autoencoders, whichcalculate low-dimensional embeddings of the surfaces. To study the deformationpatterns of unseen shapes by transfer learning, we want to train an autoencoderthat can analyze new surface meshes without training a new network. Here, moststate-of-the-art autoencoders cannot handle meshes of different connectivityand therefore have limited to no generalization capacities to new meshes. Also,reconstruction errors strongly increase in comparison to the errors for thetraining shapes. To address this, we propose a novel spectral CoSMA(Convolutional Semi-Regular Mesh Autoencoder) network. This patch-basedapproach is combined with a surface-aware training. It reconstructs surfacesnot presented during training and generalizes the deformation behavior of thesurfaces' patches. The novel approach reconstructs unseen meshes from differentdatasets in superior quality compared to state-of-the-art autoencoders thathave been trained on these shapes. Our transfer learning errors on unseenshapes are 40% lower than those from models learned directly on the data.Furthermore, baseline autoencoders detect deformation patterns of unseen meshsequences only for the whole shape. In contrast, due to the employed regionalpatches and stable reconstruction quality, we can localize where on thesurfaces these deformation patterns manifest.

Transfer Learning using Spectral Convolutional Autoencoders on Semi-Regular Surface Meshes