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

Recent advances in convolutional neural networks have shown promising resultsin 3D shape completion. But due to GPU memory limitations, these methods canonly produce low-resolution outputs. To inpaint 3D models with semanticplausibility and contextual details, we introduce a hybrid framework thatcombines a 3D Encoder-Decoder Generative Adversarial Network (3D-ED-GAN) and aLong-term Recurrent Convolutional Network (LRCN). The 3D-ED-GAN is a 3Dconvolutional neural network trained with a generative adversarial paradigm tofill missing 3D data in low-resolution. LRCN adopts a recurrent neural networkarchitecture to minimize GPU memory usage and incorporates an Encoder-Decoderpair into a Long Short-term Memory Network. By handling the 3D model as asequence of 2D slices, LRCN transforms a coarse 3D shape into a more completeand higher resolution volume. While 3D-ED-GAN captures global contextualstructure of the 3D shape, LRCN localizes the fine-grained details.Experimental results on both real-world and synthetic data show reconstructionsfrom corrupted models result in complete and high-resolution 3D objects.

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks