Reconstructing the World in Six Days

Heinly, Jared; Schönberger, Johannes L.; Dunn, Enrique; Frahm, Jan‐Michael

doi:10.1109/cvpr.2015.7298949

Cited by 144 publications

(88 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Li et al [15] introduced the concept of iconic images to model the relationship between different image clusters via iconic scene graphs. Frahm et al [6] and Heinly et al [7] further utilized the iconic representation for better scalability. Similarly, our method extends the concept of iconic images to represent visual video contents.…”

Section: Photo Collectionsmentioning

confidence: 99%

“…Frahm et al [6] reconstructed 3 million images in one day on a single computer utilizing a compact binary image representation for clustering. Recently, Heinly et al [7] pushed the envelope to tackle a world-scale dataset (100 million images) by using a streaming paradigm to identify connected images by looking at each image only once.…”

Section: Photo Collectionsmentioning

confidence: 99%

“…Iconic images, as used in Frahm et al [6] and Heinly et al [7], provide a compact yet informative summarization of the common visual elements occurring within a visual dataset. By representing videos as a histogram of iconic occurrences, we can develop efficient algorithms to discover inter-sequence relationships within a video collection.…”

Section: Introductionmentioning

confidence: 99%

“…Today, *Correspondence: kewang@cs.unc.edu 1 Department of Computer Science, UNC Chapel Hill, 201 S Columbia Street, Chapel Hill 27599, USA Full list of author information is available at the end of the article state-of-the-art methods can process static Internet photo collections for different vision tasks. For example, 3D modeling methods have striven to handle large datasets [3][4][5][6], as well as improving model robustness and completeness [7]; modern visual recognition systems can build rich feature hierarchies from large annotated image datasets [8] and perform complicated recognition tasks like image classification [9], object detection [10], and semantic segmentation [11].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient video collection association using geometry-aware Bag-of-Iconics representations

Wang

Dunn

Rodríguez

et al. 2017

IPSJ T Comput Vis Appl

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed the dramatic evolution in visual data volume and processing capabilities. For example, technical advances have enabled 3D modeling from large-scale crowdsourced photo collections. Compared to static image datasets, exploration and exploitation of Internet video collections are still largely unsolved. To address this challenge, we first propose to represent video contents using a histogram representation of iconic imagery attained from relevant visual datasets. We then develop a data-driven framework for a fully unsupervised extraction of such representations. Our novel Bag-of-Iconics (BoI) representation efficiently analyzes individual videos within a large-scale video collection. We demonstrate our proposed BoI representation with two novel applications: (1) finding video sequences connecting adjacent landmarks and aligning reconstructed 3D models and (2) retrieving geometrically relevant clips from video collections. Results on crowdsourced datasets illustrate the efficiency and effectiveness of our proposed Bag-of-Iconics representation.

show abstract

Section: Photo Collectionsmentioning

confidence: 99%

Section: Photo Collectionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient video collection association using geometry-aware Bag-of-Iconics representations

Wang

Dunn

Rodríguez

et al. 2017

IPSJ T Comput Vis Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent developments for Structure from Motion (SfM) techniques from unorganized image sets focus on large photo collections downloaded from the internet (Heinly et al, 2015;Snavely et al, 2008;Agarwal et al, 2009;Frahm et al, 2009;Havlena et al, 2010;Crandall et al, 2011). Such collections can contain thousands or even millions of images comprising a very high redundancy and often moderate baselines.…”

Section: Introductionmentioning

confidence: 99%

Efficient Wide Baseline Structure From Motion

Michelini

Mayer

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper presents a Structure from Motion approach for complex unorganized image sets. To achieve high accuracy and robustness, image triplets are employed and (an approximate) camera calibration is assumed to be known. The focus lies on a complete linking of images even in case of large image distortions, e.g., caused by wide baselines, as well as weak baselines. A method for embedding image descriptors into Hamming space is proposed for fast image similarity ranking. The later is employed to limit the number of pairs to be matched by a wide baseline method. An iterative graph-based approach is proposed formulating image linking as the search for a terminal Steiner minimum tree in a line graph. Finally, additional links are determined and employed to improve the accuracy of the pose estimation. By this means, loops in long image sequences are implicitly closed. The potential of the proposed approach is demonstrated by results for several complex image sets also in comparison with VisualSFM.

show abstract

Reconstructing 3D virtual environments within a collaborative e‐infrastructure

Coro

Palma

Ellenbroek

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Sets of two‐dimensional images are insufficient to capture the development in time and space of three‐dimensional structures. The 2D “flattening” of photographs results in a significant loss of features especially if the photos were taken by one person. Automatically collecting and aligning photos in order to render 3D structures from 2D images without specialised equipment is currently a complex process that requires specialist knowledge with often limited results. In this paper, an Open Science oriented workflow is proposed where an on‐line file system is used to share photos of an object or an environment and to produce a virtual reality scene as a navigable 3D reconstruction that can be shared with other people. Our workflow is based on a distributed e‐Infrastructure and overcomes common limitations of other approaches by having all the used technology integrated on the same platform and by not requiring specialist knowledge. A performance evaluation of the 3D reconstruction process embedded in the workflow is reported against a commercial software and an open‐source software in terms of computational efficiency and reconstruction accuracy, and three marine science use cases are reported to show potential applications of the workflow.

show abstract

Reconstructing the World in Six Days

Cited by 144 publications

References 19 publications

Efficient video collection association using geometry-aware Bag-of-Iconics representations

Efficient video collection association using geometry-aware Bag-of-Iconics representations

Efficient Wide Baseline Structure From Motion

Reconstructing 3D virtual environments within a collaborative e‐infrastructure

Contact Info

Product

Resources

About