With advancements in digital technology, the field of architectural design has increasingly embraced data and algorithms to enhance design efficiency and quality. Recent advancements in text-to-image (T2I) generation models have enabled the creation of images that correspond to textual descriptions. However, textual descriptions struggle to capture essential style characteristics in style images. In this study, we proposed a method for architectural facade design based on the stable diffusion model (SDM) that combined stylistic images or keywords as input with the structural conditions of content images to generate images with both stylistic and architectural features. By employing the constrastive language-image pre-training (CLIP) image encoder to convert the style image into its initial image embedding and feature extraction from multilayer cross-attention and training optimization to obtain a pretrained image embedding, the proposed method extracts stylistic features from style images and converts them into corresponding embeddings. This process enables the generated images to embody stylistic features and artistic semantic information. Furthermore, the T2I adapter model is employed to use the architectural structure of content images as conditional guidance, thereby ensuring that the generated images exhibit the corresponding structural features. By leveraging these two aspects, the proposed method can decorate architecture with stylistic features from stylistic images while preserving the architectural structure features of content images, resulting in images that reflect the content images after style transformation. Our method is mainly used in architectural design applications. It was capable of generating facade images from flat design drawings, three-dimensional (3D) architectural models, and hand-drawn sketches and has achieved commendable results.

3D model reconstruction is applied to an increasing number of fields related to construction, such as urban planning, mobile communication planning, solar power assessment, and so on. Previous 3D reconstruction models mostly focused on precise measurements, such as laser scanning, ultrasonic mapping, etc. Although these methods can achieve very precise results, they require specific equipment which is usually expensive. The essence of this technology is to infer the overall view of the building through pictures from the perspective that have been taken, thereby obtaining pictures from unfamiliar perspectives. This paper takes the rendering method as the starting point and learns architectural features by training a neural network to provide necessary information for rendering. Different from the more popular projection-based raster rendering method, this paper uses a point-based volume rendering method and uses light sampling to detect architectural features. This rendering method requires the color and density of specific sampling points. Therefore, this paper attempts to train a neural network to fit a five-dimensional function. The input to this function is a five-dimensional vector including position (x, y, z) and viewing direction (θ, φ) , and the output is the color and density of this point when viewed from this direction. This paper adopts the positional encoding method, which reduces the scale of the network and improves both the training speed and the rendering speed. Our method can train a usable network in dozens of seconds and render a building at 30-60 frames per second.