MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer

TL;DR

MimiCAT introduces a category-free 3D pose transfer method using a cascade-transformer that learns soft correspondences via semantic keypoints, enabling pose transfer across diverse character types with improved quality.

Contribution

The paper presents MimiCAT, a novel cascade-transformer model that enables flexible many-to-many pose transfer across different character categories using soft correspondence matching.

Findings

MimiCAT outperforms prior methods in diverse character pose transfer.

The model generalizes well to unseen character types.

Extensive experiments validate the effectiveness of the soft correspondence approach.

Abstract

3D pose transfer aims to transfer the pose-style of a source mesh to a target character while preserving both the target's geometry and the source's pose characteristic. Existing methods are largely restricted to characters with similar structures and fail to generalize to category-free settings (e.g., transferring a humanoid's pose to a quadruped). The key challenge lies in the structural and transformation diversity inherent in distinct character types, which often leads to mismatched regions and poor transfer quality. To address these issues, we first construct a million-scale pose dataset across hundreds of distinct characters. We further propose MimiCAT, a cascade-transformer model designed for category-free 3D pose transfer. Instead of relying on strict one-to-one correspondence mappings, MimiCAT leverages semantic keypoint labels to learn a novel soft correspondence that enables flexible many-to-many matching across characters. The pose transfer is then formulated as a conditional generation process, in which the source transformations are first projected onto the target through soft correspondence matching and subsequently refined using shape-conditioned representations. Extensive qualitative and quantitative experiments demonstrate that MimiCAT generalizes plausible poses across diverse character morphologies, surpassing prior approaches restricted to narrow-category transfer (e.g., humanoid-to-humanoid).