Abstract | ||
---|---|---|
We present an algorithm that takes a single frame of a person's face from a depth camera, e.g., Kinect, and produces a high-resolution 3D mesh of the input face. We leverage a dataset of 3D face meshes of 1204 distinct individuals ranging from age 3 to 40, captured in a neutral expression. We divide the input depth frame into semantically significant regions (eyes, nose, mouth, cheeks) and search the database for the best matching shape per region. We further combine the input depth frame with the matched database shapes into a single mesh that results in a high resolution shape of the input person. Our system is fully automatic and uses only depth data for matching, making it invariant to imaging conditions. We evaluate our results using ground truth shapes, as well as compare to state-of the-art shape estimation methods. We demonstrate the robustness of our local matching approach with high-quality reconstruction of faces that fall outside of the dataset span, e.g., Faces older than 40 years old, facial expressions, and different ethnicities. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/3DV.2014.67 | 3DV |
Keywords | Field | DocType |
ground truth shapes,single depth frame,image matching,face recognition,depth camera,nose,cheeks,face similarity,neutral expression,image resolution,3d face hallucination,visual databases,high-resolution 3d mesh,rgbd,face dataset,image reconstruction,eyes,local matching approach,dataset span,mouth,kinect,imaging conditions,high-quality reconstruction,facial expressions | Computer vision,Face hallucination,Polygon mesh,Computer science,Local matching,Robustness (computer science),Ground truth,Facial expression,Ranging,Artificial intelligence,Invariant (mathematics) | Conference |
Volume | Citations | PageRank |
1 | 10 | 0.44 |
References | Authors | |
25 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shu Liang | 1 | 20 | 1.32 |
Ira Kemelmacher-Shlizerman | 2 | 710 | 28.03 |
Linda G. Shapiro | 3 | 2603 | 847.56 |