Building Rome on a Cloudless Day

By Jan-Michael Frahm, Pierre Fite Georgel, David Gallup, Tim Johnson, Rahul Raguram, Changchang Wu, Yi-Hung Jen, Enrique Dunn, Brian Clipp, Svetlana Lazebnik. 2010

707 citations recorded by the source corpus.

Subfields: Geology, History, Space and Planetary Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Geology

In History

Noah Snavely

In Space and Planetary Science

Noah Snavely

Citations in the corpus

Pixelwise View Selection for Unstructured Multi-View Stereo (2016, neutral): “Large-scale 3D reconstruction from Internet photos has seen a tremendous evolution in sparse modeling using Structure-from-Motion (SfM) [1,10,21,37,39,40,45, 61] and in dense modeling using Multi-View Stereo (MVS) [2,12,13,15,42,43,59].”
Building Rome in a day (2009, background): “have built a system that uses the massive parallelism of GPUs to do city scale reconstructions on a single workstation.(7) In our system, the track generation, skeletal sets, and reconstruction algorithms are all operating on the level of connected components.”
High Accuracy and Visibility-Consistent Dense Multiview Stereo (2012, positive): “Preprocessing to remove redundant images and fast matching before calibration could be useful to accelerate the calibration [16].”
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera (2011, background): “This differentiates us from many existing reconstruction systems that support only offline reconstructions [7], real-time but non-interactive rates (e.”
Multicore bundle adjustment (2011, methodology): “An impressive demonstration is the multiGPU-based fast SfM system described in [6].”
Robust Global Translations with 1DSfM (2014, methodology): “While some earlier SfM methods were global, such as factorization [20], most current large-scale SfM systems involve sequential reconstruction [19,2,9].”
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples (2016, methodology): “The extensive retrieval-SfM reconstruction [39] of the whole dataset results in 1 , 474 reconstructed 3D models.”
Comparative Evaluation of Binary Features (2012, background): “Large-scale image registration and recognition in computer vision has led to an explosion in the amount of data being processed in simultaneous localization and mapping [1], reconstruction from photo-collections [2, 3], object recognition [4], and panorama stitching [5] applications.”
From single image query to detailed 3D reconstruction (2015, methodology): “[7, 1] extended the approach of Li et al.”
Fine-Tuning CNN Image Retrieval with No Human Annotation (2017, methodology): “ing SfM reconstruction, which is performed using the stateof-the-art SfM pipeline [60], [61], [62].”
Global, Dense Multiscale Reconstruction for a Billion Points (2015, background): “Even city scale reconstructions have become feasible [4].”
Accurate Geo-Registration by Ground-to-Aerial Image Matching (2014, methodology): “The ground-level images are collected from Flickr [1], of which roughly 10% have GPS tags [7].”
VGGT: Visual Geometry Grounded Transformer (2025, neutral): “The traditional SfM pipeline [2, 24, 48, 62, 68, 92] consists of multiple stages, including image matching, triangulation, and bundle adjustment.”
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval (2013, neutral): “For example, clustering of binary codes can be implemented using a standard k-medoids algorithm [12], while clustering in the min-hash framework is much less straightforward [7].”
Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD (2015, background): “Applications of these capabilities include adding and refining geotags in image collections [15, 41], navigation [26], photo editing [44], and 3D reconstruction [11].”