FacadeNet: Conditional Facade Synthesis via Selective Editing
This work addresses the need for realistic facade synthesis in architecture and urban planning, but it is incremental as it builds on existing GAN and vision transformer methods.
The paper tackled the problem of synthesizing building facade images from diverse viewpoints using a conditional GAN with a selective editing module, achieving state-of-the-art performance in facade generation.
We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints. Our method employs a conditional GAN, taking a single view of a facade along with the desired viewpoint information and generates an image of the facade from the distinct viewpoint. To precisely modify view-dependent elements like windows and doors while preserving the structure of view-independent components such as walls, we introduce a selective editing module. This module leverages image embeddings extracted from a pre-trained vision transformer. Our experiments demonstrated state-of-the-art performance on building facade generation, surpassing alternative methods.