New Techniques for Automated Architectural Reconstruction from Photographs

Werner, Tomáš; Zisserman, Andrew

doi:10.1007/3-540-47967-8_36

Cited by 150 publications

(132 citation statements)

References 11 publications

Supporting

Mentioning

128

Contrasting

Unclassified

Order By: Relevance

“…To perform our experiments, numerous images have been retrieved from publicly available databases [29]- [32] and also crawled from Google Images and Flickr. The collected images present challenging disparities such as combinations of different viewpoints, focal lengths, illumination variations, translations, rotations.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Region-Based Prediction for Image Compression in the Cloud

Bégaint

Thoreau

Guillotel

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

“…Multiples images were randomly aggregated to form a collection of about 700 sequences from the previously mentioned online databases [29]- [32]. This dataset present a large variety of scene contents, image resolutions and distortions: different cameras, viewpoints, conditions of illuminations, etc.…”

Section: Overall Performancementioning

confidence: 99%

Region-Based Prediction for Image Compression in the Cloud

Bégaint

Thoreau

Guillotel

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

“…To model the structure of facade objects, they use grammars, too (Werner and Zisserman, 2002;Dick et al, 2004;Alegre and Dellaert, 2004;Ripperda, 2008). Parameters of the grammar are estimated either with MCMC or directly determined during a recursive splitting and merging procedure.…”

Section: Related Workmentioning

confidence: 99%

Facade Interpretation Using a Marked Point Process

Wenzel

Förstner

2016

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

View full text Add to dashboard Cite

ABSTRACT:Our objective is the interpretation of facade images in a top-down manner, using a Markov marked point process formulated as a Gibbs process. Given single rectified facade images, we aim at the accurate detection of relevant facade objects as windows and entrances, using prior knowledge about their possible configurations within facade images. We represent facade objects by a simplified rectangular object model and present an energy model, which evaluates the agreement of a proposed configuration with the given image and the statistics about typical configurations, which we learned from training data. We show promising results on different datasets and provide a qualitative evaluation, which demonstrates the capability of complete and accurate detection of facade objects.

show abstract

“…Works on automatic reconstruction of urban scenes have mostly been based on collections of photos [3,6,8,18,20,22] or multi-view video [14], relying on photogrammetric reconstruction and image-based modeling techniques. Debevec et al [2] propose an interactive image-based modeling method that exploits characteristics of architectural objects coupling an image-based stereo algorithm with manually specified 3D model constraints.…”

Section: Related Workmentioning

confidence: 99%

2D-3D fusion for layer decomposition of urban facades

Li¹,

Zheng²,

Sharf

et al. 2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

We present a method for fusing two acquisition modes, 2D photographs and 3D LiDAR scans, for depth-layer decomposition of urban facades. The two modes have complementary characteristics: point cloud scans are coherent and inherently 3D, but are often sparse, noisy, and incomplete; photographs, on the other hand, are of high resolution, easy to acquire, and dense, but view-dependent and inherently 2D, lacking critical depth information. In this paper we use photographs to enhance the acquired LiDAR data. Our key observation is that with an initial registration of the 2D and 3D datasets we can decompose the input photographs into rectified depth layers. We decompose the input photographs into rectangular planar fragments and diffuse depth information from the corresponding 3D scan onto the fragments by solving a multi-label assignment problem. Our layer decomposition enables accurate repetition detection in each planar layer, using which we propagate geometry, remove outliers and enhance the 3D scan. Finally, the algorithm produces an enhanced, layered, textured model. We evaluate our algorithm on complex multi-planar building facades, where direct autocorrelation methods for repetition detection fail. We demonstrate how 2D photographs help improve the 3D scans by exploiting data redundancy, and transferring high level structural information to (plausibly) complete large missing regions.

show abstract

New Techniques for Automated Architectural Reconstruction from Photographs

Cited by 150 publications

References 11 publications

Region-Based Prediction for Image Compression in the Cloud

Region-Based Prediction for Image Compression in the Cloud

Facade Interpretation Using a Marked Point Process

2D-3D fusion for layer decomposition of urban facades

Contact Info

Product

Resources

About