Text-to-Vector Conversion for Residential Plan Design

TL;DR

This paper presents a new method for converting textual descriptions into vector residential plans and introduces an algorithm for vectorizing raster plans, improving visual quality and structural accuracy.

Contribution

It introduces a novel text-to-vector conversion technique for residential plans and a raster-to-vectorization algorithm, enhancing visual quality and structural fidelity.

Findings

5% improvement in CLIPScore for text-generated plans

4% better CLIPScore for vectorized raster plans

Enhanced scalability and quality in vector graphics

Abstract

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%.