用一阶优化加速三维重建，速度比传统方法快10倍
FastMap: Revisiting Structure from Motion through First-Order Optimization
- 改用一阶优化替代二阶优化，提升计算效率
- 在GPU加速下速度最高达COLMAP的10倍
- 适合需要快速重建的大规模场景应用
我们提出FastMap，一种专注于速度与简洁性的全局结构光束法。以往方法如COLMAP和GLOMAP虽能实现高精度相机位姿估计，但在匹配关键点对数量大时面临可扩展性差的问题，主要源于耗时的二阶高斯-牛顿优化过程。为此，我们仅基于一阶优化器设计新方法。为实现最大提速，我们识别并消除了两个关键性能瓶颈：计算复杂度与每步优化的内核实现。通过大量实验表明，FastMap在使用GPU加速时速度最高可达COLMAP和GLOMAP的10倍，同时保持相当的位姿精度。
原文摘要 · Abstract (English)
We propose FastMap, a new global structure from motion method focused on speed and simplicity. Previous methods like COLMAP and GLOMAP are able to estimate high-precision camera poses, but suffer from poor scalability when the number of matched keypoint pairs becomes large, mainly due to the time-consuming process of second-order Gauss-Newton optimization. Instead, we design our method solely based on first-order optimizers. To obtain maximal speedup, we identify and eliminate two key performance bottlenecks: computational complexity and the kernel implementation of each optimization step. Through extensive experiments, we show that FastMap is up to 10 times faster than COLMAP and GLOMAP with GPU acceleration and achieves comparable pose accuracy.
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。