TY - GEN
T1 - Dynamic 3-D facial compression using low rank and sparse decomposition
AU - Hou, Junhui
AU - Chau, Lap Pui
AU - He, Ying
AU - Quynh, Dao T.P.
AU - Magnenat-Thalmann, Nadia
PY - 2012/11
Y1 - 2012/11
N2 - 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.
AB - 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.
KW - Compression
KW - Dynamic 3-D facial expressions
KW - Geometry video
KW - H.264/AVC
KW - Low rank and sparse matrix decomposition
UR - http://www.scopus.com/inward/record.url?scp=84871780887&partnerID=8YFLogxK
U2 - 10.1145/2407746.2407768
DO - 10.1145/2407746.2407768
M3 - Conference article published in proceeding or book
AN - SCOPUS:84871780887
SN - 9781450319157
T3 - SIGGRAPH Asia 2012 Technical Briefs, SA 2012
BT - SIGGRAPH Asia 2012 Technical Briefs, SA 2012
T2 - SIGGRAPH Asia 2012 Technical Briefs, SA 2012
Y2 - 28 November 2012 through 1 December 2012
ER -