English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Effectively parsing the facade is essential to 3D building reconstruction,which is an important computer vision problem with a large amount ofapplications in high precision map for navigation, computer aided design, andcity generation for digital entertainments. To this end, the key is how toobtain the shape grammars from 2D images accurately and efficiently. Althoughenjoying the merits of promising results on the semantic parsing, deep learningmethods cannot directly make use of the architectural rules, which play animportant role for man-made structures. In this paper, we present a noveltranslational symmetry-based approach to improving the deep neural networks.Our method employs deep learning models as the base parser, and a module takingadvantage of translational symmetry is used to refine the initial parsingresults. In contrast to conventional semantic segmentation or bounding boxprediction, we propose a novel scheme to fuse segmentation with anchor-freedetection in a single stage network, which enables the efficient training andbetter convergence. After parsing the facades into shape grammars, we employ anoff-the-shelf rendering engine like Blender to reconstruct the realistichigh-quality 3D models using procedural modeling. We conduct experiments onthree public datasets, where our proposed approach outperforms thestate-of-the-art methods. In addition, we have illustrated the 3D buildingmodels built from 2D facade images.

Translational Symmetry-Aware Facade Parsing for 3D Building Reconstruction