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

This paper presents a novel self-supervised approach to reconstruct humanshape and pose from noisy point cloud data. Relying on large amount of datasetwith ground-truth annotations, recent learning-based approaches predictcorrespondences for every vertice on the point cloud; Chamfer distance isusually used to minimize the distance between a deformed template model and theinput point cloud. However, Chamfer distance is quite sensitive to noise andoutliers, thus could be unreliable to assign correspondences. To address theseissues, we model the probability distribution of the input point cloud asgenerated from a parametric human model under a Gaussian Mixture Model. Insteadof explicitly aligning correspondences, we treat the process of correspondencesearch as an implicit probabilistic association by updating the posteriorprobability of the template model given the input. A novel self-supervised lossis further derived which penalizes the discrepancy between the deformedtemplate and the input point cloud conditioned on the posterior probability.Our approach is very flexible, which works with both complete point cloud andincomplete ones including even a single depth image as input. Compared toprevious self-supervised methods, our method shows the capability to deal withsubstantial noise and outliers. Extensive experiments conducted on variouspublic synthetic datasets as well as a very noisy real dataset (i.e. CMUPanoptic) demonstrate the superior performance of our approach over thestate-of-the-art methods.

Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds