SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes
Open Access
- 4 December 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-11
Abstract
Animation retargetting applies sparse motion description (e.g., keypoint sequences) to a character mesh to produce a semantically plausible and temporally coherent full-body mesh sequence. Existing approaches come with restrictions - they require access to template-based shape priors or artist-designed deformation rigs, suffer from limited generalization to unseen motion and/or shapes, or exhibit motion jitter. We propose Self-supervised Motion Fields (SMF), a self-supervised framework that is trained with only sparse motion representations, without requiring dataset-specific annotations, templates, or rigs. At the heart of our method are Kinetic Codes, a novel autoencoder-based sparse motion encoding, that exposes a semantically rich latent space, simplifying large-scale training. Our architecture comprises dedicated spatial and temporal gradient predictors, which are jointly trained in an end-to-end fashion. The combined network, regularized by the Kinetic Codes' latent space, has good generalization across both unseen shapes and new motions. We evaluated our method on unseen motion sampled from AMASS, D4D, Mixamo, and raw monocular video for animation transfer on various characters with varying shapes and topology. We report a new SoTA on the AMASS dataset in the context of generalization to unseen motion.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Diffusion 3D Features (Diff3F) Decorating Untextured Shapes with Distilled Semantic Features2024
- Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry2023
- Skeleton-Free Pose Transfer for Stylized 3D Characters2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface2021
- Unsupervised Shape and Pose Disentanglement for 3D Meshes2020
- Neural Cages for Detail-Preserving 3D Deformations2020
- Deep High-Resolution Representation Learning for Human Pose Estimation2019
- Recurrent Network Models for Human Dynamics2015
- FAUST: Dataset and Evaluation for 3D Mesh Registration2014