Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving scenarios, which represent a critical aspect for overcoming utilizing synthetic data for training neural networks. We propose a method based on domain-invariant scene representation to directly synthesize traffic scene imagery without rendering. Specifically, we rely on synthetic scene graphs as our internal representation and introduce an unsupervised neural network architecture for realistic traffic scene synthesis. We enhance synthetic scene graphs with spatial information about the scene and demonstrate the effectiveness of our approach through scene manipulation.

翻译：由计算机图形学驱动的图像合成近期达到了显著的逼真度，但由此生成的合成图像数据与真实世界数据之间存在显著的领域差异。在自动驾驶场景中这一点尤为突出，而该场景对于利用合成数据训练神经网络至关重要。我们提出了一种基于领域不变场景表示的方法，无需渲染即可直接合成交通场景图像。具体而言，我们以合成场景图作为内部表示，并引入了一种用于逼真交通场景合成的无监督神经网络架构。我们通过场景的空间信息增强合成场景图，并通过场景处理展示了我们方法的有效性。