用C++/CUDA重实现3D高斯溅射，训练快17分钟，效果还更好。
ImprovedGS+: A High-Performance C++/CUDA Re-Implementation Strategy for 3D Gaussian Splatting
- 改用底层C++/CUDA内核，减少主机与设备同步开销。
- 100万高斯点配置下训练快26.8%，少用13.3%点数，视觉更优。
- 适合追求速度与质量平衡的3D重建开发者使用。
近期3D高斯溅射（3DGS）研究聚焦于重建精度与计算效率的平衡。本文提出ImprovedGS+，在LichtFeld-Studio框架中对ImprovedGS策略进行低层重实现。通过将高层Python逻辑转为硬件优化的C++/CUDA内核，显著降低主机-设备同步开销与训练延迟。引入长轴分割（LAS）CUDA内核、基于拉普拉斯的自定义重要性内核结合非极大值抑制（NMS）计算边缘得分，并设计自适应指数尺度调度器。在Mip-NeRF360数据集上的实验表明，ImprovedGS+建立了新的帕累托最优前沿。其1M预算版本相较当前最优的MCMC基线，训练时间减少26.8%（每会话节省17分钟），所用高斯点数减少13.3%，同时保持更优视觉质量；全量版本相较ADC基线提升1.28 dB PSNR，参数复杂度降低38.4%。结果验证了ImprovedGS+在速度、质量与可用性上兼具的可扩展高性能优势。
原文摘要 · Abstract (English)
Recent advancements in 3D Gaussian Splatting (3DGS) have shifted the focus toward balancing reconstruction fidelity with computational efficiency. In this work, we propose ImprovedGS+, a high-performance, low-level reinvention of the ImprovedGS strategy, implemented natively within the LichtFeld-Studio framework. By transitioning from high-level Python logic to hardware-optimized C++/CUDA kernels, we achieve a significant reduction in host-device synchronization and training latency. Our implementation introduces a Long-Axis-Split (LAS) CUDA kernel, custom Laplacian-based importance kernels with Non-Maximum Suppression (NMS) for edge scores, and an adaptive Exponential Scale Scheduler. Experimental results on the Mip-NeRF360 dataset demonstrate that ImprovedGS+ establishes a new Pareto-optimal front for scene reconstruction. Our 1M-budget variant outperforms the state-of-the-art MCMC baseline by achieving a 26.8% reduction in training time (saving 17 minutes per session) and utilizing 13.3% fewer Gaussians while maintaining superior visual quality. Furthermore, our full variant demonstrates a 1.28 dB PSNR increase over the ADC baseline with a 38.4% reduction in parametric complexity. These results validate ImprovedGS+ as a scalable, high-speed solution that upholds the core pillars of Speed, Quality, and Usability within the LichtFeld-Studio ecosystem.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。