We present WinSyn, a unique dataset and testbed for creating high-quality synthetic data with procedural modeling techniques. The dataset contains high-resolution photographs of windows, selected from locations around the world, with 89,318 individual window crops showcasing diverse geometric and material characteristics. We evaluate a procedural model by training semantic segmentation networks on both synthetic and real images and then comparing their performances on a shared test set of real images. Specifically, we measure the difference in mean Intersection over Union (mIoU) and determine the effective number of real images to match synthetic data's training performance. We design a baseline procedural model as a benchmark and provide 21,290 synthetically generated images. By tuning the procedural model, key factors are identified which significantly influence the model's fidelity in replicating real-world scenarios. Importantly, we highlight the challenge of procedural modeling using current techniques, especially in their ability to replicate the spatial semantics of real-world scenarios. This insight is critical because of the potential of procedural models to bridge to hidden scene aspects such as depth, reflectivity, material properties, and lighting conditions.

翻译：我们提出WinSyn，一个独特的用于通过程序化建模技术创建高质量合成数据的测试平台与数据集。该数据集包含从全球各地采集的高分辨率窗户照片，共计89,318个独立的窗户图像块，展示了多样化的几何与材质特征。我们通过分别在合成图像与真实图像上训练语义分割网络，并在共享的真实图像测试集上对比性能，对程序化模型进行评估。具体而言，我们测量平均交并比（mIoU）的差异，并确定匹配合成数据训练性能所需的有效真实图像数量。我们设计了一个基线程序化模型作为基准，并生成了21,290张合成图像。通过调整该程序化模型，我们识别出显著影响模型复现真实场景保真度的关键因素。重要的是，我们揭示了当前技术下程序化建模面临的挑战，尤其是其在复现真实场景空间语义方面的局限性。这一发现具有关键意义，因为程序化模型具备将深度、反射率、材质属性及光照条件等隐藏场景特征关联起来的潜力。