Eigenbubbles: An Enhanced Apparent BRDF Representation

In this paper we address the problem of relighting faces in presence of cast shadows and specularities. We present a solution to this problem by capturing the spatially varying Apparent Bidirectional Reflectance Functions (ABRDF) fields of human faces using Spline Modulated Spherical Harmonics and representing them using a few salient spherical functions called Eigenbubbles. Through extensive experiments on the Extended Yale B and the CMU PIE benchmark datasets we demonstrate that the proposed method clearly outperforms the state-of-the-art techniques in synthesized image quality. Furthermore, we show that our framework allows for ABDRF field compression and can also be used to enhance performance of face recognition algorithms. 1 Prologue Over the course of last decade, various methods have been proposed to tackle the problem of face relighting. Even though high quality results can be produced given large amount of resources (e.g. [6]), the problem is still largely unsolved when a...

• Type: Conference
• Year: 2010
• Where: ICPR
• Authors: Ritwik Kumar, Vemuri Baba, Arunava Banerjee
• Keywords: Cast Shadows, Computer Vision, ICPR 2010, Images, Salient Spherical Functions