arXiv:2606.31981v1 Announce Type: cross Abstract: Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting. We propose LUNA, an LBS-free universal neural animation model that directly maps multiple 2D controls like images, keypoints, sketches, and unseen characters into 3D Gaussian deformations, bypassing explicit body fitting. At its core, a transformer-based motion regressor disentangles global rigid motion from
Advances in AI, particularly transformer architectures and 3D Gaussian Splatting, are enabling new paradigms for realistic human animation, moving beyond traditional constraints.
This development significantly enhances the capabilities for creating highly realistic and expressive digital human avatars, impacting virtual reality, meta-communication, and entertainment industries.
The ability to generate animatable 3D human avatars from diverse 2D inputs without explicit body fitting reduces complexity and increases the photorealism and expressivity of digital humans.
- · Metaverse platforms
- · Gaming industry
- · Film and animation studios
- · Virtual reality developers
- · Traditional 3D animation studios resisting AI tools
- · Motion capture hardware companies (to a degree)
- · Legacy LBS software providers
Creation of more realistic and diverse digital human characters for various applications becomes significantly easier and more accessible.
The demand for high-fidelity digital assets for virtual environments will surge, driving innovation in content creation pipelines.
New forms of human-computer interaction and virtual social experiences may emerge, blurring lines between physical and digital presence.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI