Retrieval-Augmented Sketch-Guided 3D Building Generation

TL;DR

This paper presents a multi-stage, retrieval-augmented 3D generative framework for Japanese detached houses that improves design fidelity, supports component-level editing, and enables personalized architectural customization from sketches.

Contribution

It introduces a novel multi-stage sketch-to-3D framework combining generative and retrieval methods with component segmentation for detailed, customizable architectural models.

Findings

Enables modular customization of 3D house models

Supports component-level editing and personalized design

Demonstrates effectiveness through quantitative and expert evaluations

Abstract

In the early design stage of Japanese detached houses, the lack of a unified design representation among clients, sales representatives, and designers leads to design drift and inefficient feedback. Usually, sketches handed off by sales representatives may lose details for quick drawing, which reduces the fidelity of subsequent 3D generation using generative AI models. The generated 3D model typically takes the form of a single unified mesh, preventing component-level editing. To solve these issues, we propose a multi-stage 3D generative design framework capable of producing architectural models from rough design sketches. The framework combines generative and retrieval-based methods to enable component-level editing and personalized customization. It adopts a multimodal representation for 3D model generation and applies component segmentation to localize architectural components such as windows and doors and uses retrieval to support targeted replacement of components. Experiments show that the work enables modular customization which is thought to be suitable for personalized architectural design. This work introduces a multi-stage sketch-to-3D framework for Japanese detached houses, provides facade and component datasets, and shows effectiveness through quantitative and expert evaluations.