Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications

TL;DR

The paper addresses the challenge of producing photorealistic 3D avatars in real time on consumer devices without specialized hardware or extensive preprocessing. It introduces Instant Skinned Gaussian Avatars, which bind Gaussian splats to a background skinned mesh and update them in parallel, enabling real-time animation while preserving skinning effects. The workflow from a single smartphone video to a ready-to-use avatar takes about five minutes, with avatar generation in ~30 seconds, and is implemented as a WebXR-enabled, VRM-compatible browser application. This approach democratizes high-fidelity avatars for social, metaverse, and digital twin applications by delivering on-device, cross-platform performance with minimal user effort.

Abstract

We present Instant Skinned Gaussian Avatars, a real-time and cross-platform 3D avatar system. Many approaches have been proposed to animate Gaussian Splatting, but they often require camera arrays, long preprocessing times, or high-end GPUs. Some methods attempt to convert Gaussian Splatting into mesh-based representations, achieving lightweight performance but sacrificing visual fidelity. In contrast, our system efficiently animates Gaussian Splatting by leveraging parallel splat-wise processing to dynamically follow the underlying skinned mesh in real time while preserving high visual fidelity. From smartphone-based 3D scanning to on-device preprocessing, the entire process takes just around five minutes, with the avatar generation step itself completed in only about 30 seconds. Our system enables users to instantly transform their real-world appearance into a 3D avatar, making it ideal for seamless integration with social media and metaverse applications. Website: https://gaussian-vrm.github.io/