Skip to yearly menu bar Skip to main content


Poster

A Dataset of Relighted 3D Interacting Hands

Gyeongsik Moon · Shunsuke Saito · Weipeng Xu · Rohan Joshi · Julia Buffalini · Harley Bellan · Nicholas Rosen · Jesse Richardson · Mallorie Mize · Philippe De Bree · Tomas Simon · Bo Peng · Shubham Garg · Kevyn McPhail · Takaaki Shiratori

Great Hall & Hall B1+B2 (level 1) #224

Abstract:

The two-hand interaction is one of the most challenging signals to analyze due to the self-similarity, complicated articulations, and occlusions of hands. Although several datasets have been proposed for the two-hand interaction analysis, all of them do not achieve 1) diverse and realistic image appearances and 2) diverse and large-scale groundtruth (GT) 3D poses at the same time. In this work, we propose Re:InterHand, a dataset of relighted 3D interacting hands that achieve the two goals. To this end, we employ a state-of-the-art hand relighting network with our accurately tracked two-hand 3D poses. We compare our Re:InterHand with existing 3D interacting hands datasets and show the benefit of it. Our Re:InterHand is available in https://mks0601.github.io/ReInterHand/

Chat is not available.