Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
This work addresses the challenge of creating realistic human interaction animations for applications in animation and simulation, representing an incremental advancement by leveraging existing motion-capture data and diffusion models.
The paper tackles the problem of generating human-human interaction animations from close-proximity poses, proposing Ponimator, a framework that uses conditional diffusion models to create dynamic motion sequences and synthesize interactive poses, achieving versatility in tasks like image-based animation and text-to-interaction synthesis.
Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipate possible past and future dynamics, drawing on strong priors of human behavior. Inspired by this observation, we propose Ponimator, a simple framework anchored on proximal interactive poses for versatile interaction animation. Our training data consists of close-contact two-person poses and their surrounding temporal context from motion-capture interaction datasets. Leveraging interactive pose priors, Ponimator employs two conditional diffusion models: (1) a pose animator that uses the temporal prior to generate dynamic motion sequences from interactive poses, and (2) a pose generator that applies the spatial prior to synthesize interactive poses from a single pose, text, or both when interactive poses are unavailable. Collectively, Ponimator supports diverse tasks, including image-based interaction animation, reaction animation, and text-to-interaction synthesis, facilitating the transfer of interaction knowledge from high-quality mocap data to open-world scenarios. Empirical experiments across diverse datasets and applications demonstrate the universality of the pose prior and the effectiveness and robustness of our framework.