Interactive Character Posing by Sparse Coding

TL;DR

This paper introduces a novel sparse coding model for character posing in computer animation, enabling real-time, style-aware pose synthesis that outperforms existing methods in de-noising and completion tasks.

Contribution

It presents a new sparse coding approach that directly captures pose styles in Euclidean space, improving naturalness and efficiency in interactive character posing.

Findings

Lower de-noising and completion errors compared to existing models

Effective in real-time interactive character posing

Provides intuitive training error measurements

Abstract

Character posing is of interest in computer animation. It is difficult due to its dependence on inverse kinematics (IK) techniques and articulate property of human characters . To solve the IK problem, classical methods that rely on numerical solutions often suffer from the under-determination problem and can not guarantee naturalness. Existing data-driven methods address this problem by learning from motion capture data. When facing a large variety of poses however, these methods may not be able to capture the pose styles or be applicable in real-time environment. Inspired from the low-rank motion de-noising and completion model in \cite{lai2011motion}, we propose a novel model for character posing based on sparse coding. Unlike conventional approaches, our model directly captures the pose styles in Euclidean space to provide intuitive training error measurements and facilitate pose synthesis. A pose dictionary is learned in training stage and based on it natural poses are synthesized to satisfy users' constraints . We compare our model with existing models for tasks of pose de-noising and completion. Experiments show our model obtains lower de-noising and completion error. We also provide User Interface(UI) examples illustrating that our model is effective for interactive character posing.