FastMap: Revisiting Structure from Motion through First-Order Optimization

Jiahao Li, Haochen Wang, Muhammad Zubair Irshad, Igor Vasiljevic, Matthew Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich

Keywords: sfm, structure from motion, pose estimation, 3d reconstruction

TL;DR: A fast structure from motion method based on first-order optimization

Abstract: 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 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.

Submission Number: 310