论文标题
配对：通过成对训练基于姿势的视图综合
Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training
论文作者
论文摘要
三维面部重建是计算机视觉中流行的应用之一。但是，即使是最先进的模型仍然需要正面面部作为输入，这限制了其在野外的使用情况。面部识别也发生了类似的困境。旨在从单个侧面面部图像中恢复额叶面孔的新研究已经出现。该领域的最新面积是基于Cyclegan的面部转化生成对抗网络。这启发了我们的研究，探索了额面部合成，pix2pix和cyclean中两个模型的性能。我们对Pix2Pix上五个不同的损失函数进行了实验，以提高其性能，然后在额叶面部合成中提出一个新的网络成对器。 PAIRWIES-GAN使用两个并行的U-NET作为发电机和PatchGAN作为鉴别器。还讨论了详细的超参数。基于面部相似性比较的定量测量，我们的结果表明，与默认的Pix2Pix模型相比，具有L1损失，梯度差损失和身份损失的PIX2PIX在平均相似性的情况下取得了2.72％。此外，成对gan的性能比Cyclegan好5.4％，平均相似性比Pix2Pix高9.1％。
Three-dimensional face reconstruction is one of the popular applications in computer vision. However, even state-of-the-art models still require frontal face as inputs, which restricts its usage scenarios in the wild. A similar dilemma also happens in face recognition. New research designed to recover the frontal face from a single side-pose facial image has emerged. The state-of-the-art in this area is the Face-Transformation generative adversarial network, which is based on the CycleGAN. This inspired our research which explores the performance of two models from pixel transformation in frontal facial synthesis, Pix2Pix and CycleGAN. We conducted the experiments on five different loss functions on Pix2Pix to improve its performance, then followed by proposing a new network Pairwise-GAN in frontal facial synthesis. Pairwise-GAN uses two parallel U-Nets as the generator and PatchGAN as the discriminator. The detailed hyper-parameters are also discussed. Based on the quantitative measurement by face similarity comparison, our results showed that Pix2Pix with L1 loss, gradient difference loss, and identity loss results in 2.72% of improvement at average similarity compared to the default Pix2Pix model. Additionally, the performance of Pairwise-GAN is 5.4% better than the CycleGAN and 9.1% than the Pix2Pix at average similarity.
