Image parsing with graph grammars and Markov Random Fields applied to facade analysis

Koziński, Mateusz; Marlet, Renaud

doi:10.1109/wacv.2014.6836030

Cited by 8 publications

(4 citation statements)

References 24 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the above generic segmentation features, we include detection scores for some specific objects. Following [9,24,25], we use detectors for windows as well as doors. Whereas [9,24] fused the detection scores into the output of the pixel classifiers, we turned the detection scores into image features at every single pixel.…”

Section: Image Featuresmentioning

confidence: 99%

Efficient 2D and 3D Facade Segmentation Using Auto-Context

Gadde

Jampani

Marlet

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

show abstract

Section: Image Featuresmentioning

confidence: 99%

Efficient 2D and 3D Facade Segmentation Using Auto-Context

Gadde

Jampani

Marlet

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moving further away from hard-coded shape grammars, [35] use irregular lattices to reduce the dimensionality of the parsing problem, modeling symmetries and repetitions. [24] relaxes the Hausmannian grammar to a graph grammar where structure and position are optimized separately.…”

Section: Facade Parsingmentioning

confidence: 99%

3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Martinović

Knopp

Riemenschneider

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

122

View full text Add to dashboard Cite

We propose a new approach for semantic segmentation of 3D city models. Starting from an SfM reconstruction of a street-side scene, we perform classification and facade splitting purely in 3D, obviating the need for slow imagebased semantic segmentation methods. We show that a properly trained pure-3D approach produces high quality labelings, with significant speed benefits (20x faster) allowing us to analyze entire streets in a matter of minutes. Additionally, if speed is not of the essence, the 3D labeling can be combined with the results of a state-of-the-art 2D classifier, further boosting the performance. Further, we propose a novel facade separation based on semantic nuances between facades. Finally, inspired by the use of architectural principles for 2D facade labeling, we propose new 3D-specific principles and an efficient optimization scheme based on an integer quadratic programming formulation.

show abstract

“…Mixed continuous-discrete inference is generally used to produce good parse trees. The inference of the structure of segments can also be separated from the optimization of their size and positions [35], or be completely integrated into constraints not requiring inefficient rule sampling [36]. With this kind of methods, partially or fully occluded scene elements such as wall and windows can be recovered thanks to structural consistency.…”

Section: Related Workmentioning

confidence: 99%

Learning Grammars for Architecture-Specific Facade Parsing

2016

Self Cite

View full text Add to dashboard Cite

International audienceParsing facade images requires optimal handcrafted grammar for a given class of buildings. Such a handcrafted grammar is often designed manually by experts. In this paper, we present a novel framework to learn a compact grammar from a set of ground-truth images. To this end, parse trees of ground-truth annotated images are obtained running existing inference algorithms with a simple, very general grammar. From these parse trees, repeated subtrees are sought and merged together to share derivations and produce a grammar with fewer rules. Furthermore, unsupervised clustering is performed on these rules, so that, rules corresponding to the same complex pattern are grouped together leading to a rich compact grammar. Experimental validation and comparison with the state-of-the-art grammar-based methods on four different datasets show that the learned grammar helps in much faster convergence while producing equal or more accurate parsing results compared to handcrafted grammars as well as grammars learned by other methods. Besides, we release a new dataset of facade images following the Art-deco style and demonstrate the general applicability and extreme potential of the proposed framework

show abstract

Image parsing with graph grammars and Markov Random Fields applied to facade analysis

Cited by 8 publications

References 24 publications

Efficient 2D and 3D Facade Segmentation Using Auto-Context

Efficient 2D and 3D Facade Segmentation Using Auto-Context

3D all the way: Semantic segmentation of urban scenes from start to end in 3D

Learning Grammars for Architecture-Specific Facade Parsing

Contact Info

Product

Resources

About