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

Human shape estimation is an important task for video editing, animation andfashion industry. Predicting 3D human body shape from natural images, however,is highly challenging due to factors such as variation in human bodies,clothing and viewpoint. Prior methods addressing this problem typically attemptto fit parametric body models with certain priors on pose and shape. In thiswork we argue for an alternative representation and propose BodyNet, a neuralnetwork for direct inference of volumetric body shape from a single image.BodyNet is an end-to-end trainable network that benefits from (i) a volumetric3D loss, (ii) a multi-view re-projection loss, and (iii) intermediatesupervision of 2D pose, 2D body part segmentation, and 3D pose. Each of themresults in performance improvement as demonstrated by our experiments. Toevaluate the method, we fit the SMPL model to our network output and showstate-of-the-art results on the SURREAL and Unite the People datasets,outperforming recent approaches. Besides achieving state-of-the-artperformance, our method also enables volumetric body-part segmentation.

BodyNet: Volumetric Inference of 3D Human Body Shapes