VkSplat: High-Performance 3DGS Training in Vulkan Compute
Not on the map. Why?
Abstract (arXiv)
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: hrefhttps://github.com/harry7557558/vksplathttps://github.com/harry7557558/vksplat
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 13 references that are in the map. First posted on arXiv 30 Apr 2026.
Builds on
11 of 13 references.
References · 11
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
- 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 217
- 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
- 2024StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Renderingcited by 111
- 2024Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitivescited by 95
- 2025FastGS: Training 3D Gaussian Splatting in 100 Secondscited by 43
- 2025TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Corescited by 12
- 2025Efficient Differentiable Hardware Rasterization for 3D Gaussian Splattingcited by 6
- 2025Moment-Based 3D Gaussian Splatting: Resolving Volumetric Occlusion with Order-Independent Transmittancecited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.