BMVC 2004, Kingston, 7th-9th Sept, 2004
Face Inpainting with Local Linear Representations
Z. Mo, J.P. Lewis and U. Neumann (University of Southern California)
A number of investigators have had success using domain specific prior knowledge to produce
improved superresolution images of faces ("hallucinating faces"). These efforts address
the scenario where a face image is obtained from a low-resolution camera. A related
but less studied problem occurs when the missing information is the result of occlusion
rather than low camera resolution, as in the case when a person is wearing sunglasses.
Recently Hwang and Lee  introduced the first algorithm for solving this reconstruction
"inpainting" problem. In the current work we report results of a psychological study
that provides independent evidence regarding the validity of the face reconstruction task,
and we demonstrate an improved reconstruction approach using a positive, local linear
representation. The positive, local mixture operates on real-world images without manual
intervention in many cases, and provides demonstrably lower reconstruction error than is
obtainable with a global representation.