Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

TL;DR

Make-It-Poseable introduces a skinning-free, latent-space transformation framework for 3D character posing, improving accuracy, flexibility, and generalization across diverse shapes and applications.

Contribution

It presents a novel feed-forward approach that decouples shape deformation from mesh topology, enabling robust, zero-shot pose generalization and topological flexibility.

Findings

Outperforms existing methods in pose quality

Exhibits zero-shot generalization to quadrupeds

Supports diverse 3D authoring tasks

Abstract

Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, frequently struggle with inaccurate skinning weights, fixed mesh topologies, and poor pose conformance. These challenges have become particularly pronounced with the recent explosion of AI-generated 3D assets, which often exhibit flawed structures and fused geometry. To address these issues, we introduce Make-It-Poseable, a novel feed-forward framework that reformulates character posing as a skinning-free latent-space transformation problem. By decoupling shape deformation from the constraints of fixed mesh connectivity, our method directly operates on compact latent representations to reconstruct characters in target poses. To achieve this, our framework integrates a latent posing transformer for shape manipulation, a dense pose representation for fine-grained control, and an adaptive completion module optimized via a bipartite-matched latent loss to robustly handle topological changes. Extensive experiments demonstrate that our method significantly outperforms existing baselines in posing quality. Furthermore, our skeleton-agnostic design exhibits remarkable zero-shot generalization to diverse morphologies including quadrupeds and seamlessly supports various 3D authoring applications such as part replacement and refinement.