Shape grammar parsing via Reinforcement Learning

Authors:
O. Teboul;I. Kokkinos;L. Simon;P. Koutsourakis;N. Paragios
Affiliations:
Lab. MAS, Ecole Centrale Paris, Paris, France;Lab. MAS, Ecole Centrale Paris, Paris, France;Lab. MAS, Ecole Centrale Paris, Paris, France;Lab. MAS, Ecole Centrale Paris, Paris, France;Lab. MAS, Ecole Centrale Paris, Paris, France
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 9

Adaptive partitioning of urban facades

Proceedings of the 2011 SIGGRAPH Asia Conference
Interactive Coherence-Based Façade Modeling

Computer Graphics Forum
Learning domain knowledge for façade labelling

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
A three-layered approach to facade parsing

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Online Detection of Repeated Structures in Point Clouds of Urban Scenes for Compression and Registration

International Journal of Computer Vision
Layered analysis of irregular facades via symmetry maximization

ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
Quasi-regular facade structure extraction

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part IV
Technical Section: Automatic urban modeling using volumetric reconstruction with surface graph cuts

Computers and Graphics
Semantizing complex 3D scenes using constrained attribute grammars

SGP '13 Proceedings of the Eleventh Eurographics/ACMSIGGRAPH Symposium on Geometry Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address shape grammar parsing for facade segmentation using Reinforcement Learning (RL). Shape parsing entails simultaneously optimizing the geometry and the topology (e.g. number of floors) of the facade, so as to optimize the fit of the predicted shape with the responses of pixel-level 'terminal detectors'. We formulate this problem in terms of a Hierarchical Markov Decision Process, by employing a recursive binary split grammar. This allows us to use RL to efficiently find the optimal parse of a given facade in terms of our shape grammar. Building on the RL paradigm, we exploit state aggregation to speedup computation, and introduce image-driven exploration in RL to accelerate convergence. We achieve state-of-the-art results on facade parsing, with a significant speed-up compared to existing methods, and substantial robustness to initial conditions. We demonstrate that the method can also be applied to interactive segmentation, and to a broad variety of architectural styles.