Neural Motion Blending Across Arbitrary Character Topologies
2026-07-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionGraphics
AI summaryⓘ
The authors developed a new way to blend character motions even when the characters have different bone structures. They use a special encoder to turn each frame of motion into a simple code, and a decoder that rebuilds the motion for each specific character. By mixing these codes from two motions, they create smooth blended animations. They tested their method on a dataset with various skeleton types, showing it works well for different characters.
motion blendingcharacter animationskeleton topologylatent representationsemantic encoderdiffusion decodermotion interpolationTruebones Zoo dataset
Authors
Luca Cazzola, Giulia Martinelli, Nicola Conci
Abstract
Motion blending in character animation enables the synthesis of new motions by interpolating between existing examples. Current methods are typically restricted to fixed skeleton topologies, requiring identical or near-identical skeletal structures across characters. We present a novel framework for motion blending across heterogeneous skeletons. The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder, which reconstructs character-specific motion conditioned on this latent code. At inference, blended motions are obtained by interpolating the latent representations of two input motions. We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies, demonstrating the ability to achieve smooth and plausible blending in a variety of scenarios.