用生成模型去噪并识别3D人脸点云，准确率最高提升14.81%。
Face recognition on point cloud with cgan-top for denoising
- 设计cGAN-TOP模型，从三个正交平面联合去噪点云
- 在Bosphorus数据集上，所有噪声条件下识别准确率均提升，最高增14.81%
- 适合做3D人脸识别且点云含噪的场景，如安防或医疗建模
基于3D点云的人脸识别日益受到关注，但原始点云常因传感器不完善而包含大量噪声。本文提出一种端到端的3D人脸识别方法，将去噪与识别模块协同整合。具体地，设计了基于三正交平面的条件生成对抗网络（cGAN-TOP），有效去除点云噪声并恢复潜在特征以供后续识别；随后采用改进的链式动态图卷积神经网络（LDGCNN）从处理后的点云中识别人脸，该网络分层关联多尺度的局部点特征与邻域特征。所提方法在Bosphorus数据集上验证，所有噪声设置下识别准确率均有显著提升，最大增益达14.81%。
原文摘要 · Abstract (English)
Face recognition using 3D point clouds is gaining growing interest, while raw point clouds often contain a significant amount of noise due to imperfect sensors. In this paper, an end-to-end 3D face recognition on a noisy point cloud is proposed, which synergistically integrates the denoising and recognition modules. Specifically, a Conditional Generative Adversarial Network on Three Orthogonal Planes (cGAN-TOP) is designed to effectively remove the noise in the point cloud, and recover the underlying features for subsequent recognition. A Linked Dynamic Graph Convolutional Neural Network (LDGCNN) is then adapted to recognize faces from the processed point cloud, which hierarchically links both the local point features and neighboring features of multiple scales. The proposed method is validated on the Bosphorus dataset. It significantly improves the recognition accuracy under all noise settings, with a maximum gain of 14.81%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。