Summary
UniMate is a unified foundation model for skeletal animation, presented by researchers including Linzhan Mou, Jiahui Lei, and Zhiyang Dou (arXiv:2609.05415). While automatic rigging advances now produce animation-ready 3D assets at scale, generating motion to drive them remains a bottleneck, and existing learned animators are topology-constrained—relying on category-specific templates or requiring per-skeleton fine-tuning and reference motions at inference. UniMate synthesizes articulated motion for arbitrary skeletons directly from a rigged 3D asset and a text prompt, requiring no test-time optimization or per-skeleton retraining. Its core is a topology-aware diffusion transformer that integrates skeletal topology into attention through three mechanisms: a graph-aware attention bias derived from pairwise joint relations and geodesic distances, a spectral rotary position embedding generalizing RoPE, and a third topology-integration mechanism. The approach aims to make text-driven 3D character animation generalizable across diverse skeleton topologies.
Paper Overview
- Field: Computer Vision (CV)
- Authors: Linzhan Mou, Jiahui Lei, Zhiyang Dou, Chenyue Cai, Chaoyue Song, Adam Finkelstein, Szymon Rusinkiewicz
- Published: 2026-09-04
- arXiv: 2609.05415
Abstract
Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Existing learned animators are topology-constrained: they rely on category-specific templates or require per-skeleton fine-tuning and reference motions at inference.
We present UniMate, a unified foundation model that synthesizes articulated motion for arbitrary skeletons from a rigged 3D asset and a text prompt, with no test-time optimization or per-skeleton retraining. UniMate introduces a topology-aware diffusion transformer, which integrates skeletal topology into attention via three mechanisms:
1. A graph-aware attention bias from pairwise joint relations and geodesic distances;
2. A spectral rotary position embedding generalizing RoPE to skeletal structures;
3. A third topology-integration mechanism (truncated in the source post).
*Note: the abstract in the source post is truncated; details of the third mechanism and experimental results are available in the full paper.*
---
*Auto-collected on 2026-09-08.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634617