TY - JOUR
T1 - Using 3D face priors for depth recovery
AU - Chen, Chongyu
AU - Pham, Hai Xuan
AU - Pavlovic, Vladimir
AU - Cai, Jianfei
AU - Shi, Guangming
AU - Gao, Yuefang
AU - Cheng, Hui
PY - 2017/10
Y1 - 2017/10
N2 - For repairing inaccurate depth measurements from commodity RGB-D sensors, existing depth recovery methods primarily rely on low-level and rigid prior information. However, as the depth quality deteriorates, the recovered depth maps become increasingly unreliable, especially for non-rigid objects. Thus, additional high-level and non-rigid information is needed to improve the recovery quality. Taking as a starting point the human face that is the primary prior available in many high-level tasks, in this paper, we incorporate face priors into the depth recovery process. In particular, we propose a joint optimization framework that consists of two main steps: transforming the face model for better alignment and applying face priors for improved depth recovery. Face priors from both sparse and dense 3D face models are studied. By comparing with the baseline method on benchmark datasets, we demonstrate that the proposed method can achieve up to 23.8% improvement in depth recovery with more accurate face registrations, bringing inspirations to both non-rigid object modeling and analysis.
AB - For repairing inaccurate depth measurements from commodity RGB-D sensors, existing depth recovery methods primarily rely on low-level and rigid prior information. However, as the depth quality deteriorates, the recovered depth maps become increasingly unreliable, especially for non-rigid objects. Thus, additional high-level and non-rigid information is needed to improve the recovery quality. Taking as a starting point the human face that is the primary prior available in many high-level tasks, in this paper, we incorporate face priors into the depth recovery process. In particular, we propose a joint optimization framework that consists of two main steps: transforming the face model for better alignment and applying face priors for improved depth recovery. Face priors from both sparse and dense 3D face models are studied. By comparing with the baseline method on benchmark datasets, we demonstrate that the proposed method can achieve up to 23.8% improvement in depth recovery with more accurate face registrations, bringing inspirations to both non-rigid object modeling and analysis.
KW - Depth recovery
KW - Face model
KW - Image restoration
UR - http://www.scopus.com/inward/record.url?scp=85020757551&partnerID=8YFLogxK
U2 - 10.1016/j.jvcir.2017.06.002
DO - 10.1016/j.jvcir.2017.06.002
M3 - Article
AN - SCOPUS:85020757551
VL - 48
SP - 16
EP - 29
JO - Journal of Visual Communication and Image Representation
JF - Journal of Visual Communication and Image Representation
SN - 1047-3203
ER -