VkSplat: High-Performance 3DGS Training in Vulkan Compute

arXiv:2605.00219v1 Announce Type: new 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 3.3imes 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: href{https://github.com/harry7557558/vksplat}{https://github.com/harry7557558/vksplat}

Source: arXiv cs.CV | 2026-05-04