ViRAC: A Vision-Reasoning Agent Head Movement Control Framework in Arbitrary Virtual Environments

TL;DR

ViRAC is a framework that uses large-scale vision and language models to generate natural, context-aware head movements for virtual agents, improving realism without explicit cognitive modeling.

Contribution

Introduces ViRAC, a novel approach leveraging pre-trained models' biases for realistic head movement control in virtual agents, surpassing prior data-driven and saliency-based methods.

Findings

Produces more natural head rotations than state-of-the-art methods.

Aligns closely with human head-movement data.

User studies confirm enhanced realism and plausibility.

Abstract

Creating lifelike virtual agents capable of interacting with their environments is a longstanding goal in computer graphics. This paper addresses the challenge of generating natural head rotations, a critical aspect of believable agent behavior for visual information gathering and dynamic responses to environmental cues. Although earlier methods have made significant strides, many rely on data-driven or saliency-based approaches, which often underperform in diverse settings and fail to capture deeper cognitive factors such as risk assessment, information seeking, and contextual prioritization. Consequently, generated behaviors can appear rigid or overlook critical scene elements, thereby diminishing the sense of realism. In this paper, we propose \textbf{ViRAC}, a \textbf{Vi}sion-\textbf{R}easoning \textbf{A}gent Head Movement \textbf{C}ontrol framework, which exploits the common-sense knowledge and reasoning capabilities of large-scale models, including Vision-Language Models (VLMs) and Large-Language Models (LLMs). Rather than explicitly modeling every cognitive mechanism, ViRAC leverages the biases and patterns internalized by these models from extensive training, thus emulating human-like perceptual processes without hand-tuned heuristics. Experimental results in multiple scenarios reveal that ViRAC produces more natural and context-aware head rotations than recent state-of-the-art techniques. Quantitative evaluations show a closer alignment with real human head-movement data, while user studies confirm improved realism and cognitive plausibility.