CALM: Conditional Adversarial Latent Models for Directable Virtual Characters

Abstract

In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters. Using imitation learning, CALM learns a representation of movement that captures the complexity and diversity of human motion, and enables direct control over character movements. The approach jointly learns a control policy and a motion encoder that reconstructs key characteristics of a given motion without merely replicating it. The results show that CALM learns a semantic motion representation, enabling control over the generated motions and style-conditioning for higher-level task training. Once trained, the character can be controlled using intuitive interfaces, akin to those found in video games.

arXiv commentAccepted to SIGGRAPH 2023

References in corpus (6)

• DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
• NormFace: L2 Hypersphere Embedding for Face Verification
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• Character Controllers Using Motion VAEs
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
• PADL: Language-Directed Physics-Based Character Control

Cited by in corpus (5)

• C$\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters
• Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs
• AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
• CBIL: Collective Behavior Imitation Learning for Fish from Real Videos
• SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control