Posing 3D characters is a fundamental task in computer graphics and vision. However, existing methods like auto-rigging and pose-conditioned generation often struggle with challenges such as inaccurate skinning weight prediction, topological imperfections, and poor pose conformance, limiting their robustness and generalizability.
To overcome these limitations, we introduce Make-It-Poseable, a novel feed-forward framework that reformulates character posing as a latent-space transformation problem. Instead of deforming mesh vertices as in traditional pipelines, our method reconstructs the character in new poses by directly manipulating its latent representation. At the core of our method is a latent posing transformer that manipulates shape tokens based on skeletal motion. This process is facilitated by a dense pose representation for precise control. To ensure high-fidelity geometry and accommodate topological changes, we also introduce a latent-space supervision strategy and an adaptive completion module.
Our method demonstrates superior performance in posing quality. It also naturally extends to 3D editing applications like part replacement and refinement.
(a) The skeleton encoder produces dense pose representations with latent-level one-to-one
correspondence.
(b) Latent-space supervision ensures a semantically meaningful token transformation path to
preserve
geometric details.
(c) Adaptive tokens are introduced in the finetuning stage to handle newly exposed structures after
deformation.
Make-It-Poseable produces high-fidelity results across various cases. It robustly handles challenging inputs where auto-rigging methods produce significant artifacts, and gives better pose conformance and detail preservation compared to the pose-conditioned 3D generation method.
A Gradio-based demo for interactive posing workflow:
Make-It-Poseable can facilitate character animation in two ways:
(1) First re-pose the input mesh into a rest pose with limbs fully extended (effectively resolving the
skinning and topology issues), then rig and animate it using standard workflows.
(2) Directly apply target motions to generate a mesh sequence, leveraging our method's detail consistency
and fast speed.
The fine-grained control offered by our latent-space modeling also enables some 3D editing applications such as segmentation, replacement, and refinement of body parts.
@article{guo2025make,
author={Guo, Zhiyang and Zhang, Ran and Xiang, Jinxu and Zhao, Alan and Zhou, Wengang and Li, Houqiang},
title={Make-It-Poseable: Feed-forward Latent Posing Model for 3D Humanoid Character Animation},
journal={arXiv preprint arXiv:2512.16767},
year={2025},
}