论文标题
上下文一致的语义图像编辑，并保留样式的调制
Context-Consistent Semantic Image Editing with Style-Preserved Modulation
论文作者
论文摘要
语义图像编辑利用本地语义标签图在编辑区域生成所需的内容。最近的一项工作借用了Spade Block来实现语义图像编辑。但是，由于编辑的区域和周围像素之间的样式差异，它无法产生令人愉悦的结果。我们将其归因于以下事实：Spade仅使用与图像无关的局部语义布局，但忽略了已知像素中包含的图像特定样式。为了解决此问题，我们提出了一个样式保存的调制（SPM），其中包括两个调制过程：第一个调制包含上下文样式和语义布局，然后生成两个融合的调制参数。第二个调制采用融合参数来调制特征图。通过使用此类调制，SPM可以在保留特定图像的上下文样式的同时注入给定的语义布局。此外，我们设计了一种渐进式体系结构，以粗到精细的方式生成编辑的内容。提出的方法可以获得上下文一致的结果，并显着减轻生成区域和已知像素之间的不愉快边界。
Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region. A recent work borrows SPADE block to achieve semantic image editing. However, it cannot produce pleasing results due to style discrepancy between the edited region and surrounding pixels. We attribute this to the fact that SPADE only uses an image-independent local semantic layout but ignores the image-specific styles included in the known pixels. To address this issue, we propose a style-preserved modulation (SPM) comprising two modulations processes: The first modulation incorporates the contextual style and semantic layout, and then generates two fused modulation parameters. The second modulation employs the fused parameters to modulate feature maps. By using such two modulations, SPM can inject the given semantic layout while preserving the image-specific context style. Moreover, we design a progressive architecture for generating the edited content in a coarse-to-fine manner. The proposed method can obtain context-consistent results and significantly alleviate the unpleasant boundary between the generated regions and the known pixels.
