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

Realistic reconstruction of two hands interacting with objects is a new andchallenging problem that is essential for building personalized Virtual andAugmented Reality environments. Graph Convolutional networks (GCNs) allow forthe preservation of the topologies of hands poses and shapes by modeling themas a graph. In this work, we propose the THOR-Net which combines the power ofGCNs, Transformer, and self-supervision to realistically reconstruct two handsand an object from a single RGB image. Our network comprises two stages; namelythe features extraction stage and the reconstruction stage. In the featuresextraction stage, a Keypoint RCNN is used to extract 2D poses, features maps,heatmaps, and bounding boxes from a monocular RGB image. Thereafter, this 2Dinformation is modeled as two graphs and passed to the two branches of thereconstruction stage. The shape reconstruction branch estimates meshes of twohands and an object using our novel coarse-to-fine GraFormer shape network. The3D poses of the hands and objects are reconstructed by the other branch using aGraFormer network. Finally, a self-supervised photometric loss is used todirectly regress the realistic textured of each vertex in the hands' meshes.Our approach achieves State-of-the-art results in Hand shape estimation on theHO-3D dataset (10.0mm) exceeding ArtiBoost (10.8mm). It also surpasses othermethods in hand pose estimation on the challenging two hands and object (H2O)dataset by 5mm on the left-hand pose and 1 mm on the right-hand pose.

THOR-Net: End-to-end Graformer-based Realistic Two Hands and Object Reconstruction with Self-supervision