Publications

Abstract : The objective of this research is the rapid reconstruction of ancient buildings of historical importanceusing a single image. The key idea of our approach is to reduce the infinite solutions that might otherwise arisewhen recovering a 3D geometry from 2D photographs. The main outcome of our research shows that the proposedmethodology can be used to reconstruct ancient monuments for use as proxies for digital effects in applications suchas tourism, games, and entertainment, which do not require very accurate modeling. In this article, we considerthe reconstruction of ancient Mughal architecture including the Taj Mahal. We propose a modeling pipeline thatmakes an easy reconstruction possible using a single photograph taken from a single view, without the need to createcomplex point clouds from multiple images or the use of laser scanners. First, an initial model is automaticallyreconstructed using locally fitted planar primitives along with their boundary polygons and the adjacency relationamong parts of the polygons. This approach is faster and more accurate than creating a model from scratch becausethe initial reconstruction phase provides a set of structural information together with the adjacency relation, whichmakes it possible to estimate the approximate depth of the entire structural monument. Next, we use manualextrapolation and editing techniques with modeling software to assemble and adjust different 3D components ofthe model. Thus, this research opens up the opportunity for the present generation to experience remote sites ofarchitectural and cultural importance through virtual worlds and real-time mobile applications. Variations of arecreated 3D monument to represent an amalgam of various cultures are targeted for future work.