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.
Motion blending remains a core tool in character animation, yet standard workflows are still largely constrained by fixed skeleton representations. When characters differ in topology, proportions, or hierarchy, artists often need manual correspondence design, retargeting, and substantial cleanup before they can explore even simple blended motions. We present BlendAnything, a Blender plugin that brings cross-topology motion blending into a familiar animation workflow. The plugin is powered by a skeleton-agnostic diffusion autoencoding backend that maps motions from different skeletal structures into a learned shared per-frame latent space, where high-level motion attributes such as action, phase, and global pose dynamics can be interpolated independently of rig topology, and then decodes the result into motion that remains structurally compatible with the chosen output skeleton. This design allows users to select reference and target motions, control the transition, and preview cross-topology blends directly inside Blender. We demonstrate the approach on the Truebones Zoo dataset with both quantitative and qualitative results in in-skeleton and cross-skeleton settings. By embedding this capability into Blender, BlendAnything turns cross-topology motion blending into a practical authoring tool for animation.