Building Rome on a cloudless day

Authors:
Jan-Michael Frahm;Pierre Fite-Georgel;David Gallup;Tim Johnson;Rahul Raguram;Changchang Wu;Yi-Hung Jen;Enrique Dunn;Brian Clipp;Svetlana Lazebnik;Marc Pollefeys
Affiliations:
University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science;University of North Carolina at Chapel Hill, Department of Computer Science and ETH Zürich, Department of Computer Science
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Year:
2010

Citing 17
Cited 41

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?"

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Multiple View Geometry in Computer Vision

Multiple View Geometry in Computer Vision
An Efficient Solution to the Five-Point Relative Pose Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Scalable Recognition with a Vocabulary Tree

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Fast Compact City Modeling for Navigation Pre-Visualization

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions

Communications of the ACM - 50th anniversary issue: 1958 - 2008
Detailed Real-Time Urban 3D Reconstruction from Video

International Journal of Computer Vision
Modeling the World from Internet Photo Collections

International Journal of Computer Vision
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Object Mining Using a Matching Graph on Very Large Image Collections

ICVGIP '08 Proceedings of the 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing
Accurate, Dense, and Robust Multiview Stereopsis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-resolution real-time stereo on commodity graphics hardware

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Determining an initial image pair for fixing the scale of a 3d reconstruction from an image sequence

DAGM'06 Proceedings of the 28th conference on Pattern Recognition

Motion capture from body-mounted cameras

ACM SIGGRAPH 2011 papers
PhotoCity: training experts at large-scale image acquisition through a competitive game

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Scene-based image retrieval by transitive matching

Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Building Rome in a day

Communications of the ACM
Fusion of depth maps with multiple scales

Proceedings of the 2011 SIGGRAPH Asia Conference
Maximum likelihood autocalibration

Image and Vision Computing
Efficient city-sized 3D reconstruction from ultra-high resolution aerial and ground video imagery

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
3D reconstruction of buildings with automatic facade refinement

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera

Proceedings of the 24th annual ACM symposium on User interface software and technology
A public system for image based 3D model generation

MIRAGE'11 Proceedings of the 5th international conference on Computer vision/computer graphics collaboration techniques
Sorting unorganized photo sets for urban reconstruction

Graphical Models
Videoscapes: exploring sparse, unstructured video collections

ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
Creating Large-Scale City Models from 3D-Point Clouds: A Robust Approach with Hybrid Representation

International Journal of Computer Vision
Dense 3D point cloud generation from multiple high-resolution spherical images

VAST'11 Proceedings of the 12th International conference on Virtual Reality, Archaeology and Cultural Heritage
SURE: surface entropy for distinctive 3d features

SC'12 Proceedings of the 2012 international conference on Spatial Cognition VIII
MatchMiner: efficient spanning structure mining in large image collections

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Covariance propagation and next best view planning for 3d reconstruction

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Comparative evaluation of binary features

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Scale robust multi view stereo

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Visibility probability structure from sfm datasets and applications

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Learning to match images in large-scale collections

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Generalized subgraph preconditioners for large-scale bundle adjustment

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Towards fast image-based localization on a city-scale

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Dense 3d reconstruction from wide baseline image sets

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
On performance analysis of optical flow algorithms

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
On the evaluation of scene flow estimation

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
3D heritage on mobile devices: scenarios and opportunities

EuroMed'12 Proceedings of the 4th international conference on Progress in Cultural Heritage Preservation
Practical time bundle adjustment for 3d reconstruction on the GPU

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Fast organization of large photo collections using CUDA

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Rotation-invariant fast features for large-scale recognition and real-time tracking

Image Communication
Semantic decomposition and reconstruction of residential scenes from LiDAR data

ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Optimizing color consistency in photo collections

ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Label transfer exploiting three-dimensional structure for semantic segmentation

Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Applications
Stable two view reconstruction using the six-point algorithm

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Adaptive structure from motion with a contrario model estimation

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
A novel unsupervised approach for multilevel image clustering from unordered image collection

Frontiers of Computer Science: Selected Publications from Chinese Universities
3D Scene Reconstruction from Multiple Spherical Stereo Pairs

International Journal of Computer Vision
Technical Section: Automatic urban modeling using volumetric reconstruction with surface graph cuts

Computers and Graphics
Driving in an augmented-city: from fast and automatic large scale environment modeling to on-line 6DOF vehicle localization

Proceedings of the 12th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry
Large-scale Structure-from-Motion Reconstruction with small memory consumption

Proceedings of International Conference on Advances in Mobile Computing & Multimedia
Online reconstruction of textured triangle meshes from aerial images

UDMV '13 Proceedings of the Eurographics Workshop on Urban Data Modelling and Visualisation

Quantified Score

Hi-index	0.02

Visualization

Abstract

This paper introduces an approach for dense 3D reconstruction from unregistered Internet-scale photo collections with about 3 million images within the span of a day on a single PC ("cloudless"). Our method advances image clustering, stereo, stereo fusion and structure from motion to achieve high computational performance. We leverage geometric and appearance constraints to obtain a highly parallel implementation on modern graphics processors and multi-core architectures. This leads to two orders of magnitude higher performance on an order of magnitude larger dataset than competing state-of-the-art approaches.