Computer Science

News and events

28 October 2011

3D Reconstruction of Buildings From Photographs

Presented By Dr Francho Melendez, Research Associate, Department of Computer Science, Loughborough University
  • 3.00pm
  • Room N225, Haslegrave

About this event

Abstract: Aquisition of realistic and relightable 3D models of large outdoor objects, such as buildings, requires the modelling of detailed geometry and visual appearance. Recovering these material characteristics can be very time consuming and requires specially dedicated equipment. Alternatively, surface detail is conveyed by textures recovered from images, whose appearance is only valid under the originally photographed viewing and lighting conditions. Methods to easily capture local detailed surface, such as cracks in stone walls, and visual appearance, require control of lighting conditions, which restricts them to small portions of the surface captured at close range. This work investigates the acquisition high-quality models from images, using simple photographic equipment and modest user intervention.

We propose a complete image-based process that facilitates recovery of both gross scale geometry and local surface structure to create highly detailed 3D models of building façades from photographs. We approximate both albedo and sufficient local geometric structure to compute complex self-shadowing effects, and fuse this with a gross scale 3D model. Our approach yields a perceptually high-quality model, imparting the illusion of measured reflectance.

The requirements of our approach are that image capture must be performed under diffuse lighting and surfaces in the images must be predominantly Lambertian. Exemplars of materials are obtained through surface depth hallucination and our novel method matches these with multi-view image sequences that are also used to automatically recover 3D geometry.