ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics

Boris Oreshkin · Florent Bocquelet · Felix G. Harvey · Bay Raitt · Dominic Laflamme

[ Abstract ] [ Livestream: Visit Oral 1: AI Applications ]
Mon 25 Apr 5:45 p.m. — 6 p.m. PDT
[ OpenReview

Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling. Specifically, we tackle the problem of constructing a full static human pose based on sparse and variable user inputs (e.g. locations and/or orientations of a subset of body joints). To solve this problem, we propose a novel neural architecture that combines residual connections with prototype encoding of a partially specified pose to create a new complete pose from the learned latent space. We show that our architecture outperforms a baseline based on Transformer, both in terms of accuracy and computational efficiency. Additionally, we develop a user interface to integrate our neural model in Unity, a real-time 3D development platform. Furthermore, we introduce two new datasets representing the static human pose modeling problem, based on high-quality human motion capture data, which will be released publicly along with model code.

Chat is not available.