Variational shape and reflectance estimation under changing light and viewpoints

  • Authors:
  • Neil Birkbeck;Dana Cobzas;Peter Sturm;Martin Jagersand

  • Affiliations:
  • Computer Science, University of Alberta, Canada;Computer Science, University of Alberta, Canada;INRIA Rhone-Alpes, France;Computer Science, University of Alberta, Canada

  • Venue:
  • ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Fitting parameterized 3D shape and general reflectance models to 2D image data is challenging due to the high dimensionality of the problem. The proposed method combines the capabilities of classical and photometric stereo, allowing for accurate reconstruction of both textured and non-textured surfaces. In particular, we present a variational method implemented as a PDE-driven surface evolution interleaved with reflectance estimation. The surface is represented on an adaptive mesh allowing topological change. To provide the input data, we have designed a capture setup that simultaneously acquires both viewpoint and light variation while minimizing self-shadowing. Our capture method is feasible for real-world application as it requires a moderate amount of input data and processing time. In experiments, models of people and everyday objects were captured from a few dozen images taken with a consumer digital camera. The capture process recovers a photo-consistent model of spatially varying Lambertian and specular reflectance and a highly accurate geometry.