Text-to-Vector Conversion for Residential Plan Design
This addresses the need for scalable vector graphics in design and architecture, though it appears incremental with specific numerical gains.
The paper tackles the problem of generating vector residential plans from textual descriptions, achieving approximately 5% higher CLIPScore-based visual quality than existing solutions, and also presents a vectorization algorithm that improves CLIPscore by about 4% for raster plans.
Computer graphics, comprising both raster and vector components, is a fundamental part of modern science, industry, and digital communication. While raster graphics offer ease of use, its pixel-based structure limits scalability. Vector graphics, defined by mathematical primitives, provides scalability without quality loss, however, it is more complex to produce. For design and architecture, the versatility of vector graphics is paramount, despite its computational demands. This paper introduces a novel method for generating vector residential plans from textual descriptions. Our approach surpasses existing solutions by approximately 5% in CLIPScore-based visual quality, benefiting from its inherent handling of right angles and flexible settings. Additionally, we present a new algorithm for vectorizing raster plans into structured vector images. Such images have a better CLIPscore compared to others by about 4%.