Face Relighting from a Single Image under Arbitrary Unknown Lighting Conditions

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 31; no. 11; pp. 1968 - 1984
• Main Authors: Yang Wang, Lei Zhang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengyou Zhang, Samaras, D.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.11.2009; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3D spherical harmonic basis morphable model; Albedo; Algorithms; Applied sciences; Approximation error; Artificial Intelligence; Biometry - methods; Computer graphics; Computer science; control theory; systems; Exact sciences and technology; Face - anatomy & histology; Face detection; Face recognition; Face synthesis and recognition; Humans; Illumination; Image databases; Image Enhancement - methods; Image generation; Image Interpretation, Computer-Assisted - methods; Lighting; Lighting - methods; Markov random field; Markov random fields; Mathematical models; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Photography - methods; Reproducibility of Results; Sensitivity and Specificity; Shape; Spherical harmonics; Subtraction Technique; Surface layer; Texture; vision for graphics; Modeling and recovery of physical attributes; Face and gesture recognition; Markov process; Statistical analysis; Spherical shape; Probabilistic approach; Face recognition; Image processing; 3D spherical harmonic basis morphable model; Worst case method; Markov model; Pattern recognition; Markov random field; Modeling; Texture; Graphics; Luminance; Albedo; Vector space; Lighting; Face synthesis and recognition; Facies; Illumination; Approximation error; Spherical harmonic; vision for graphics

In this paper, we present a new method to modify the appearance of a face image by manipulating the illumination condition, when the face geometry and albedo information is unknown. This problem is particularly difficult when there is only a single image of the subject available. Recent research dem...