The Year in AI Papers
The year/Independent research

Paper 2512.08478

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

Yuning Gong, Yifei Liu, Yifan Zhan, Muyao Niu, Xueying Li, Yuanjun Liao, Jiaming Chen, Yuanyuan Gao, Jiaqi Chen, Minming Chen, Li Zhou, Yuning Zhang, et al.

Published
Dec 2025
Research lab
Independent
Citations
2
GitHub
517 stars

01 In brief

Summary

Visionary is an open, web-native platform for real-time rendering of 3D Gaussian Splatting (3DGS) and meshes, built on WebGPU and ONNX.

It introduces a Gaussian Generator contract, a standardized ONNX I/O interface that allows plug-and-play integration of various 3DGS algorithms (e.g., MLP-based 3DGS, 4DGS, neural avatars) without modifying the renderer.

The platform performs per-frame ONNX inference and GPU-based sorting, achieving up to ~135x speedup over WebGL-based viewers like SparkJS while maintaining rendering quality.

It also supports generative post-processing and offers a three.js plugin for integration.

Experiments show Visionary sustains real-time performance across static and dynamic scenes, with inference times of 7-8ms for avatars and 4-16ms for other variants.

The platform aims to serve as a unified World Model Carrier for both reconstructive and generative paradigms, with future work on physics-aware modeling and embodied AI.

02 From the paper

Abstract

Neural rendering, particularly 3D Gaussian Splatting (3DGS), has evolved rapidly and become a key component for building world models. However, existing viewer solutions remain fragmented, heavy, or constrained by legacy pipelines, resulting in high deployment friction and limited support for dynamic content and generative models. In this work, we present Visionary, an open, web-native platform for real-time various Gaussian Splatting and meshes rendering. Built on an efficient WebGPU renderer with per-frame ONNX inference, Visionary enables dynamic neural processing while maintaining a lightweight, "click-to-run" browser experience. It introduces a standardized Gaussian Generator contract, which not only supports standard 3DGS rendering but also allows plug-and-play algorithms to generate or update Gaussians each frame. Such inference also enables us to apply feedforward generative post-processing. The platform further offers a plug in three.js library with a concise TypeScript API for seamless integration into existing web applications. Experiments show that, under identical 3DGS assets, Visionary achieves superior rendering efficiency compared to current Web viewers due to GPU-based primitive sorting. It already supports multiple variants, including MLP-based 3DGS, 4DGS, neural avatars, and style transformation or enhancement networks. By unifying inference and rendering directly in the browser, Visionary significantly lowers the barrier to reproduction, comparison, and deployment of 3DGS-family methods, serving as a unified World Model Carrier for both reconstructive and generative paradigms.