Journal Article10.1145/2001269.2001293
Building Rome in a day
Sameer Agarwal,Yasutaka Furukawa,Noah Snavely,Ian Simon,Brian Curless,Steven M. Seitz,Richard Szeliski +6 more
TL;DR: A system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city on Internet photo sharing sites and is designed to scale gracefully with both the size of the problem and the amount of available computation.
read more
Abstract: We present a system that can reconstruct 3D geometry from large, unorganized collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo-sharing sites. Our system is built on a set of new, distributed computer vision algorithms for image matching and 3D reconstruction, designed to maximize parallelism at each stage of the pipeline and to scale gracefully with both the size of the problem and the amount of available computation. Our experimental results demonstrate that it is now possible to reconstruct city-scale image collections with more than a hundred thousand images in less than a day.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Hybrid Scene Compression for Visual Localization
TL;DR: In this article, a hybrid compression algorithm is proposed to obtain a more complete scene representation without increasing the memory requirements, leading to a superior performance compared to previous compression schemes. But, it does not handle ambiguous matches arising from point compression during RANSAC.
2
•Posted Content
ANSAC: Adaptive Non-minimal Sample and Consensus
TL;DR: ANSAC as discussed by the authors is a RANSAC-based estimator that accounts for noise by adaptively using more than the minimal number of correspondences required to generate a hypothesis.
2
Self-localizing smart cameras and their applications
Babak Shirmohammadi
- 01 Jan 2012
TL;DR: This dissertation has successfully used its custom made self localizing smart camera networks to implement a novel decentralized target tracking algorithm, create an ad-hoc range finder and localize the components of a self assembling modular robot.
2
•Posted Content
Correspondence Networks with Adaptive Neighbourhood Consensus.
TL;DR: In this article, the adaptive neighbourhood consensus network (ANC-Net) is proposed to establish dense visual correspondences between images containing objects of the same category, which can be trained end-to-end with sparse key-point annotations.
2
BAFT: Binary affine feature transform
Jonas Toft Arnfred,Viet Dung Nguyen,Stefan Winkler +2 more
- 27 Sep 2017
TL;DR: BAFT combines the affine invariance of Harris Affine feature descriptors with the speed of binary descriptors such as BRISK and ORB to result in a fast but discriminative descriptor, especially for image pairs with large perspective changes.
2
References
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
•Book
Multiple view geometry in computer vision
Richard Hartley,Andrew Zisserman +1 more
- 01 Jan 2000
TL;DR: In this article, the authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly in a unified framework, including geometric principles and how to represent objects algebraically so they can be computed and applied.
20.1K
Video Google: a text retrieval approach to object matching in videos
TL;DR: An approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video, represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion.
Related Papers (5)
Richard Hartley,Andrew Zisserman +1 more
- 01 Jan 2000
Johannes L. Schonberger,Jan-Michael Frahm +1 more
- 27 Jun 2016
Bill Triggs,Philip F. McLauchlan,Richard Hartley,Andrew Fitzgibbon +3 more
- 21 Sep 1999