3D Face Hallucination from a Single Depth Frame.
3D Face Hallucination from a Single Depth Frame.
复制标题
DOI：
10.1109/3dv.2014.67
复制
发表时间：
2014-12
期刊：
影响因子：
--
通讯作者：
Shapiro LG
中科院分区：
文献类型：
--
作者：
Liang S;Kemelmacher-Shlizerman I;Shapiro LG
我们提出了一种算法，该算法从深度相机（例如Kinect）中获取人脸的单帧，并生成输入人脸的高分辨率3D网格。我们利用1204个年龄从3岁到40岁的不同个体的3D面部网格数据集，以中性表情捕获。我们将输入深度帧划分为语义上重要的区域（眼睛，鼻子，嘴巴，脸颊），并在数据库中搜索每个区域的最佳匹配形状。我们进一步将输入深度帧与匹配的数据库形状组合成一个网格，从而得到输入人物的高分辨率形状。我们的系统是全自动的，只使用深度数据进行匹配，使其不受成像条件的影响。我们使用地面真值形状评估我们的结果，并与最先进的形状估计方法进行比较。我们通过对数据集范围之外的人脸进行高质量重建来证明我们的局部匹配方法的鲁棒性，例如，年龄超过40岁的人脸、面部表情和不同的种族。
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 highresolution 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.