论文标题
Vologan：对综合深度数据的对抗域的适应
VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Data
论文作者
论文摘要
我们提出了Vologan，这是一个对抗性域的适应网络，该网络将一个人的高质量3D模型的合成RGB-D图像转化为可以使用消费者深度传感器生成的RGB-D图像。该系统对于为单视3D重建算法生成大量训练数据特别有用，该算法复制了现实世界中的捕获条件，能够模仿相同的高端3D模型数据库的不同传感器类型的样式。该网络使用Cyclegan框架，其中具有用于发电机的U-NET体系结构，以及受SIV-GAN启发的歧视器。我们使用不同的优化者和学习率时间表来训练发电机和鉴别器。我们进一步构建了一个单独考虑图像通道的损失函数，除其他指标外，还评估了结构相似性。我们证明，自行车型可用于应用合成3D数据的对抗结构域适应，以训练只有少量训练样本的体积视频发电机模型。
We present VoloGAN, an adversarial domain adaptation network that translates synthetic RGB-D images of a high-quality 3D model of a person, into RGB-D images that could be generated with a consumer depth sensor. This system is especially useful to generate high amount training data for single-view 3D reconstruction algorithms replicating the real-world capture conditions, being able to imitate the style of different sensor types, for the same high-end 3D model database. The network uses a CycleGAN framework with a U-Net architecture for the generator and a discriminator inspired by SIV-GAN. We use different optimizers and learning rate schedules to train the generator and the discriminator. We further construct a loss function that considers image channels individually and, among other metrics, evaluates the structural similarity. We demonstrate that CycleGANs can be used to apply adversarial domain adaptation of synthetic 3D data to train a volumetric video generator model having only few training samples.
