FastMap: Revisiting Dense and Scalable Structure from Motion

Jiahao Li*1, Haochen Wang*1, Muhammad Zubair Irshad2, Igor Vasiljevic2, Matthew R. Walter1, Vitor Campagnolo Guizilini†2, Greg Shakhnarovich†1


1TTIC    2Toyota Research Institute
Paper Code

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. We identify two key factors leading to this problem: poor parallelization and computationally expensive optimization steps. To overcome these issues, we design an SfM framework that relies entirely on GPU-friendly operations, making it easily parallelizable. Moreover, each optimization step runs in time linear to the number of image pairs, independent of keypoint pairs or 3D points. Through extensive experiments, we show that FastMap is one to two orders of magnitude faster than COLMAP and GLOMAP on large-scale scenes with comparable pose accuracy.

diagram

Speed Comparison

Pose Accuracy

NeRF and Gaussian Splatting

More Results

MipNeRF360
Tanks & Temples
DroneDeploy
NeRF-OSR
ZipNeRF
Mill-19
UrbanScene3D
Eyeful Tower

BibTeX


@article{2505.04612v1,
    Author        = {Jiahao Li and Haochen Wang and Muhammad Zubair Irshad and Igor Vasiljevic and Matthew R. Walter and Vitor Campagnolo Guizilini and Greg Shakhnarovich},
    Title         = {FastMap: Revisiting Dense and Scalable Structure from Motion},
    Eprint        = {2505.04612v1},
    ArchivePrefix = {arXiv},
    PrimaryClass  = {cs.CV},
    Year          = {2025},
    Month         = {May},
    Url           = {http://arxiv.org/abs/2505.04612v1},
    File          = {2505.04612v1.pdf}
}