FacaDiffy: Inpainting Unseen Facade Parts Using Diffusion Models

TL;DR

FacaDiffy introduces a novel approach combining deterministic ray analysis and personalized diffusion models to inpaint unseen facade parts, significantly improving conflict map completion and 3D building reconstruction accuracy.

Contribution

The paper presents a new method for inpainting unseen facade parts using personalized diffusion models and a scalable pipeline for synthetic data generation.

Findings

Achieves state-of-the-art conflict map completion performance.

Increases detection rate by 22% in 3D building reconstruction.

Demonstrates effectiveness of personalized diffusion models for facade inpainting.

Abstract

High-detail semantic 3D building models are frequently utilized in robotics, geoinformatics, and computer vision. One key aspect of creating such models is employing 2D conflict maps that detect openings' locations in building facades. Yet, in reality, these maps are often incomplete due to obstacles encountered during laser scanning. To address this challenge, we introduce FacaDiffy, a novel method for inpainting unseen facade parts by completing conflict maps with a personalized Stable Diffusion model. Specifically, we first propose a deterministic ray analysis approach to derive 2D conflict maps from existing 3D building models and corresponding laser scanning point clouds. Furthermore, we facilitate the inpainting of unseen facade objects into these 2D conflict maps by leveraging the potential of personalizing a Stable Diffusion model. To complement the scarcity of real-world training data, we also develop a scalable pipeline to produce synthetic conflict maps using random city model generators and annotated facade images. Extensive experiments demonstrate that FacaDiffy achieves state-of-the-art performance in conflict map completion compared to various inpainting baselines and increases the detection rate by $22\%$ when applying the completed conflict maps for high-definition 3D semantic building reconstruction. The code is be publicly available in the corresponding GitHub repository: https://github.com/ThomasFroech/InpaintingofUnseenFacadeObjects