Neural Motion Blending Across Arbitrary Character Topologies

• URL: http://arxiv.org/abs/2607.10370v1
• Date: Sat, 11 Jul 2026 15:46:13 GMT
• Title: Neural Motion Blending Across Arbitrary Character Topologies
• Abstract summary: We present a novel framework for motion blending across heterogeneous skeletons.<n>The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder.<n>We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies.
• Score: 7.503125656408304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes [52.45449797329548]
  MotionDreamer is a diffusion-based framework for category-agnostic skeletal animation generation from 2D video guidance.<n>We propose a structural-semantic injection mechanism to bridge the gap between 2D visual motion cues and heterogeneous 3D skeletal structures.<n>Our approach significantly outperforms existing methods, setting a new state-of-the-art benchmark for robust and efficient 4D asset generation.
  arXiv  Detail & Related papers  (2026-06-01T00:42:31Z)
• Training-free Motion Factorization for Compositional Video Generation [57.819757612370374]
  We propose a motion factorization framework that decomposes complex motion into three primary categories: motionlessness, rigid motion, and non-rigid motion.<n>Our framework achieves impressive performance in motion synthesis on real-world benchmarks.
  arXiv  Detail & Related papers  (2026-03-10T02:27:48Z)
• AnyTop: Character Animation Diffusion with Any Topology [54.07731933876742]
  We introduce AnyTop, a diffusion model that generates motions for diverse characters with distinct motion dynamics.<n>Our work features a transformer-based denoising network, tailored for arbitrary skeleton learning.<n>Our evaluation demonstrates that AnyTops well, even with as few as three training examples per topology, and can produce motions for unseen skeletons as well.
  arXiv  Detail & Related papers  (2025-02-24T17:00:36Z)
• Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space [28.628241993271647]
  We propose a generative motion stylization pipeline, named MotionS, for diverse and stylized motion on cross-structure characters. Our key insight is to embed motion style into a cross-modality latent space, allowing for motion stylization within a canonical motion space.
  arXiv  Detail & Related papers  (2024-03-18T04:41:59Z)
• MoDi: Unconditional Motion Synthesis from Diverse Data [51.676055380546494]
  We present MoDi, an unconditional generative model that synthesizes diverse motions. Our model is trained in a completely unsupervised setting from a diverse, unstructured and unlabeled motion dataset. We show that despite the lack of any structure in the dataset, the latent space can be semantically clustered.
  arXiv  Detail & Related papers  (2022-06-16T09:06:25Z)
• Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video [5.456297943378056]
  We present Neural Marionette, an unsupervised approach that discovers the skeletal structure from a dynamic sequence. We demonstrate that the discovered structure is even comparable to the hand-labeled ground truth in skeleton representing a 4D sequence of motion.
  arXiv  Detail & Related papers  (2022-02-17T02:44:16Z)
• Hierarchical Style-based Networks for Motion Synthesis [150.226137503563]
  We propose a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by decomposing a long-range generation task in a hierarchical manner. On large-scale skeleton dataset, we show that the proposed method is able to synthesise long-range, diverse and plausible motion.
  arXiv  Detail & Related papers  (2020-08-24T02:11:02Z)
• Skeleton-Aware Networks for Deep Motion Retargeting [83.65593033474384]
  We introduce a novel deep learning framework for data-driven motion between skeletons. Our approach learns how to retarget without requiring any explicit pairing between the motions in the training set.
  arXiv  Detail & Related papers  (2020-05-12T12:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.