Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911310199914496 |
|---|---|
| author | Gong, Yuning Liu, Yifei Zhan, Yifan Niu, Muyao Li, Xueying Liao, Yuanjun Chen, Jiaming Gao, Yuanyuan Chen, Jiaqi Chen, Minming Zhou, Li Zhang, Yuning Wang, Wei Hou, Xiaoqing Huang, Huaxi Tang, Shixiang Ma, Le Zhang, Dingwen Yang, Xue Yan, Junchi Zhang, Yanchi Zheng, Yinqiang Sun, Xiao Zhong, Zhihang |
| author_facet | Gong, Yuning Liu, Yifei Zhan, Yifan Niu, Muyao Li, Xueying Liao, Yuanjun Chen, Jiaming Gao, Yuanyuan Chen, Jiaqi Chen, Minming Zhou, Li Zhang, Yuning Wang, Wei Hou, Xiaoqing Huang, Huaxi Tang, Shixiang Ma, Le Zhang, Dingwen Yang, Xue Yan, Junchi Zhang, Yanchi Zheng, Yinqiang Sun, Xiao Zhong, Zhihang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08478 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Gong, Yuning Liu, Yifei Zhan, Yifan Niu, Muyao Li, Xueying Liao, Yuanjun Chen, Jiaming Gao, Yuanyuan Chen, Jiaqi Chen, Minming Zhou, Li Zhang, Yuning Wang, Wei Hou, Xiaoqing Huang, Huaxi Tang, Shixiang Ma, Le Zhang, Dingwen Yang, Xue Yan, Junchi Zhang, Yanchi Zheng, Yinqiang Sun, Xiao Zhong, Zhihang Computer Vision and Pattern Recognition Artificial Intelligence Graphics 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. |
| title | Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2512.08478 |