用学习的高斯初始化加速3D表面重建，提升精度与速度。
QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
- 通过数据驱动方法生成高斯初始分布，替代传统手动设置。
- 运行时间快8倍，深度误差降低48%，优于当前最优方法。
- 自适应添加新高斯点，无需人工设定规则，适合大场景重建。
表面重建是计算机视觉与图形学的基础任务，广泛应用于3D建模、混合现实和机器人等领域。现有基于体素渲染的方法虽效果良好，但需逐场景优化，耗时长且难以处理观测不足或无纹理区域。本文提出QuickSplat，利用数据驱动先验生成2D高斯泼溅优化的大规模室内场景密集初始化，为重建提供优良起点，显著加快收敛速度并改善平面墙体结构精度。我们进一步设计联合优化网络，在每轮迭代中同时估计稀疏化与参数更新；提出的密度增强网络根据现有高斯的渲染梯度预测新增高斯点，避免依赖启发式规则。在大规模室内场景重建上的大量实验表明，本方法显著优于现有技术：运行时间提速8倍，深度误差最大降低48%。
原文摘要 · Abstract (English)
Surface reconstruction is fundamental to computer vision and graphics, enabling applications in 3D modeling, mixed reality, robotics, and more. Existing approaches based on volumetric rendering obtain promising results, but optimize on a per-scene basis, resulting in a slow optimization that can struggle to model under-observed or textureless regions. We introduce QuickSplat, which learns data-driven priors to generate dense initializations for 2D gaussian splatting optimization of large-scale indoor scenes. This provides a strong starting point for the reconstruction, which accelerates the convergence of the optimization and improves the geometry of flat wall structures. We further learn to jointly estimate the densification and update of the scene parameters during each iteration; our proposed densifier network predicts new Gaussians based on the rendering gradients of existing ones, removing the needs of heuristics for densification. Extensive experiments on large-scale indoor scene reconstruction demonstrate the superiority of our data-driven optimization. Concretely, we accelerate runtime by 8x, while decreasing depth errors by up to 48% in comparison to state of the art methods.
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。