VkSplat: High-Performance 3DGS Training in Vulkan Compute
Loading...
Date
2026
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present VkSplat, a high-performance, cross-vendor 3D Gaussian Splatting (3DGS) training pipeline implemented fully in Vulkan compute, addressing performance and compatibility limitation of existing training pipelines. With various optimizations, we achieve 3.3× speed and 33% VRAM reduction over CUDA+PyTorch baseline, maintaining quality, and demonstrating compatibility across GPU vendors. To the best of our knowledge, this is the first fully-Vulkan-based 3DGS training pipeline that achieves state-of-the-art performance. Code: https://github.com/harry7557558/vksplat
Description
@inproceedings{10.2312:egs.20261024,
booktitle = {Eurographics 2026 - Short Papers},
editor = {},
title = {{VkSplat: High-Performance 3DGS Training in Vulkan Compute}},
author = {Chen, Jingxiang and Ibrahim, Mohamed and Liu, Yang},
year = {2026},
publisher = {The Eurographics Association},
ISSN = {2309-5059},
ISBN = {978-3-03868-299-8},
DOI = {10.2312/egs.20261024}
}