Dynamic 3-D facial compression using low rank and sparse decomposition

Abstract

In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique. Then, low rank and sparse decomposition is applied to each dimension (i.e., X, Y and Z, respectively) before the H.264/AVC encoder is employed to separately encode each dimension instead of encoding them as a whole. Experimental results show that the averaged 3-4 dB gain is achieved by the proposed scheme compared with existing algorithms.