论文标题
Stylandgan：使用深度图的基于样式的景观图像合成
StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map
论文作者
论文摘要
尽管有条件图像合成最近的成功，但诸如语义和边缘等流行的输入条件还不够清晰，无法表达“线性（脊）”和“平面（比例）”表示。为了解决这个问题，我们提出了一个新型的框架Stylandgan，该框架使用具有较高表达能力的深度图综合了所需的景观图像。我们的Stylelandgan从无条件的生成模型扩展到接受输入条件。我们还提出了一个“ 2阶段推理”管道，该管道会生成各种深度图并移动本地零件，从而可以轻松地反映用户的意图。作为比较，我们修改了现有的语义图像合成模型，以接受深度图。实验结果表明，我们的方法优于质量，多样性和深度准确性的现有方法。
Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express `Linear (Ridges)' and `Planar (Scale)' representations. To address this problem, we propose a novel framework StyLandGAN, which synthesizes desired landscape images using a depth map which has higher expressive power. Our StyleLandGAN is extended from the unconditional generation model to accept input conditions. We also propose a '2-phase inference' pipeline which generates diverse depth maps and shifts local parts so that it can easily reflect user's intend. As a comparison, we modified the existing semantic image synthesis models to accept a depth map as well. Experimental results show that our method is superior to existing methods in quality, diversity, and depth-accuracy.
