UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation

2026-03-26

AI Summary

Traditional physics-based simulation is computationally expensive and unsuitable for real-time applications, while existing learning-based approaches still struggle to accurately model fine-grained deformations of garments with complex topologies. This work proposes UNIC, a method that constructs a character-specific neural deformation field to map 3D spatial points to pose-driven deformation offsets, enabling high-quality, real-time garment animation. By employing an instance-specific implicit representation, UNIC avoids the need for generalization to new garments and only requires adaptation to new poses. Moreover, it bypasses explicit mesh processing, inherently ensuring smooth deformations. Experiments demonstrate that UNIC significantly outperforms current baselines across a variety of complex garments, achieving superior performance in both deformation fidelity and computational efficiency, making it well-suited for real-time interactive scenarios such as gaming.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Simulating physically realistic garment deformations is an essential task for virtual immersive experience, which is often achieved by physics simulation methods. However, these methods are typically time-consuming, computationally demanding, and require costly hardware, which is not suitable for real-time applications. Recent learning-based methods tried to resolve this problem by training graph neural networks to learn the garment deformation on vertices, which, however, fail to capture the intricate deformation of complex garment meshes with complex topologies. In this paper, we introduce a novel neural deformation field-based method, named UNIC, to animate the garments of an avatar in real time, given the motion sequences. Our key idea is to learn the instance-specific neural deformation field to animate the garment meshes. Such an instance-specific learning scheme does not require UNIC to generalize to new garments but only to new motion sequences, which greatly reduces the difficulty in training and improves the deformation quality. Moreover, neural deformation fields map the 3D points to their deformation offsets, which not only avoids handling topologies of the complex garments but also injects a natural smoothness constraint in the deformation learning. Extensive experiments have been conducted on various kinds of garment meshes to demonstrate the effectiveness and efficiency of UNIC over baseline methods, making it potentially practical and useful in real-world interactive applications like video games.

Problem

• garment deformation
• real-time animation
• neural deformation field
• clothed character
• complex topology

Innovation

• neural deformation field
• instance-specific learning
• real-time cloth animation
• topology-agnostic deformation
• garment simulation