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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recovering the 3D shape of an object from single or multiple images with deepneural networks has been attracting increasing attention in the past few years.Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) tosequentially fuse feature maps of input images. However, RNN-based approachesare unable to produce consistent reconstruction results when given the sameinput images with different orders. Moreover, RNNs may forget importantfeatures from early input images due to long-term memory loss. To address theseissues, we propose a novel framework for single-view and multi-view 3D objectreconstruction, named Pix2Vox++. By using a well-designed encoder-decoder, itgenerates a coarse 3D volume from each input image. A multi-scale context-awarefusion module is then introduced to adaptively select high-qualityreconstructions for different parts from all coarse 3D volumes to obtain afused 3D volume. To further correct the wrongly recovered parts in the fused 3Dvolume, a refiner is adopted to generate the final output. Experimental resultson the ShapeNet, Pix3D, and Things3D benchmarks show that Pix2Vox++ performsfavorably against state-of-the-art methods in terms of both accuracy andefficiency.

Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images