快速收敛的3D高斯点撒法用于1分钟重建
Fast Converging 3D Gaussian Splatting for 1-Minute Reconstruction
AI总结：
本文提出了一种快速收敛的3D高斯点撒方法，通过两阶段方案在1分钟内实现高保真重建，取得PSNR 28.43的优异成绩。
摘要：
我们提出了一种快速的3DGS重建管道，旨在在1分钟内收敛，该管道为SIGGRAPH Asia 3DGS快速重建挑战而设计。该挑战包括一个使用SLAM生成的相机姿态（带有噪声轨迹）的初步轮次和一个使用COLMAP姿态（高度准确）的最终轮次。为了稳健地处理这些异构设置，我们开发了两阶段的解决方案。在第一轮中，我们使用反向每高斯并行优化和基于Taming-GS和Speedy-splat的紧凑前向点撒，负载均衡的瓦片，基于锚点的Neural-Gaussian表示，使快速收敛，使用更少的可学习参数，从单目深度初始化并部分从馈送前向3DGS模型初始化，以及一个全局姿态细化模块用于噪声SLAM轨迹。在最终轮次中，准确的COLMAP姿态改变了优化景观；我们禁用姿态细化，从Neural-Gaussians回退到标准3DGS以消除MLP推理开销，引入多视图一致性引导的高斯分裂，灵感来自Fast-GS，并引入深度估计器来监督渲染深度。这些技术共同使在严格的一分钟预算下实现高保真重建。我们的方法在PSNR为28.43的情况下取得了最高性能，并在比赛中排名第一。
英文摘要：
We present a fast 3DGS reconstruction pipeline designed to converge within one minute, developed for the SIGGRAPH Asia 3DGS Fast Reconstruction Challenge. The challenge consists of an initial round using SLAM-generated camera poses (with noisy trajectories) and a final round using COLMAP poses (highly accurate). To robustly handle these heterogeneous settings, we develop a two-stage solution. In the first round, we use reverse per-Gaussian parallel optimization and compact forward splatting based on Taming-GS and Speedy-splat, load-balanced tiling, an anchor-based Neural-Gaussian representation enabling rapid convergence with fewer learnable parameters, initialization from monocular depth and partially from feed-forward 3DGS models, and a global pose refinement module for noisy SLAM trajectories. In the final round, the accurate COLMAP poses change the optimization landscape; we disable pose refinement, revert from Neural-Gaussians back to standard 3DGS to eliminate MLP inference overhead, introduce multi-view consistency-guided Gaussian splitting inspired by Fast-GS, and introduce a depth estimator to supervise the rendered depth. Together, these techniques enable high-fidelity reconstruction under a strict one-minute budget. Our method achieved the top performance with a PSNR of 28.43 and ranked first in the competition.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
