AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction

Three-dimensional urban reconstruction of buildings from single-view images has attracted significant attention over the past two decades. However, recent methods primarily focus on rooftops from aerial images, often overlooking essential geometrical details. Additionally, there is a notable lack of...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Turki, D. Panangian, H. Chaabouni-Chouayakh, K. Bittner
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1477/2025/isprs-archives-XLVIII-G-2025-1477-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849412592115646464
author S. Turki
S. Turki
D. Panangian
H. Chaabouni-Chouayakh
K. Bittner
author_facet S. Turki
S. Turki
D. Panangian
H. Chaabouni-Chouayakh
K. Bittner
author_sort S. Turki
collection DOAJ
description Three-dimensional urban reconstruction of buildings from single-view images has attracted significant attention over the past two decades. However, recent methods primarily focus on rooftops from aerial images, often overlooking essential geometrical details. Additionally, there is a notable lack of datasets containing complete 3D point clouds for entire buildings, along with challenges in obtaining reliable camera pose information for aerial images. This paper addresses these challenges by presenting a novel methodology, AIM2PC , which utilizes our generated dataset that includes complete 3D point clouds and determined camera poses. Our approach takes features from a single aerial image as input and concatenates them with essential additional conditions, such as binary masks and Sobel edge maps, to enable more edge-aware reconstruction. By incorporating a point cloud diffusion model based on Centered denoising Diffusion Probabilistic Models (CDPM), we project these concatenated features onto the partially denoised point cloud using our camera poses at each diffusion step. The proposed method is able to reconstruct the complete 3D building point cloud, including wall information and demonstrates superior performance compared to existing baseline techniques. To allow further comparisons with our methodology the dataset has been made available at <code>https://github.com/Soulaimene/AIM2PCDataset</code>.
format Article
id doaj-art-4be76a58db384a7982d13590576a4530
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-4be76a58db384a7982d13590576a45302025-08-20T03:34:24ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251477148410.5194/isprs-archives-XLVIII-G-2025-1477-2025AIM2PC: Aerial Image to 3D Building Point Cloud ReconstructionS. Turki0S. Turki1D. Panangian2H. Chaabouni-Chouayakh3K. Bittner4Remote Sensing Technology Institute, German Aerospace Center (DLR), Wessling, GermanyHigher School of Communication of Tunis, TunisiaRemote Sensing Technology Institute, German Aerospace Center (DLR), Wessling, GermanySm@rts Laboratory, Digital Research Center of Sfax, TunisiaRemote Sensing Technology Institute, German Aerospace Center (DLR), Wessling, GermanyThree-dimensional urban reconstruction of buildings from single-view images has attracted significant attention over the past two decades. However, recent methods primarily focus on rooftops from aerial images, often overlooking essential geometrical details. Additionally, there is a notable lack of datasets containing complete 3D point clouds for entire buildings, along with challenges in obtaining reliable camera pose information for aerial images. This paper addresses these challenges by presenting a novel methodology, AIM2PC , which utilizes our generated dataset that includes complete 3D point clouds and determined camera poses. Our approach takes features from a single aerial image as input and concatenates them with essential additional conditions, such as binary masks and Sobel edge maps, to enable more edge-aware reconstruction. By incorporating a point cloud diffusion model based on Centered denoising Diffusion Probabilistic Models (CDPM), we project these concatenated features onto the partially denoised point cloud using our camera poses at each diffusion step. The proposed method is able to reconstruct the complete 3D building point cloud, including wall information and demonstrates superior performance compared to existing baseline techniques. To allow further comparisons with our methodology the dataset has been made available at <code>https://github.com/Soulaimene/AIM2PCDataset</code>.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1477/2025/isprs-archives-XLVIII-G-2025-1477-2025.pdf
spellingShingle S. Turki
S. Turki
D. Panangian
H. Chaabouni-Chouayakh
K. Bittner
AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
title_full AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
title_fullStr AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
title_full_unstemmed AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
title_short AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction
title_sort aim2pc aerial image to 3d building point cloud reconstruction
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1477/2025/isprs-archives-XLVIII-G-2025-1477-2025.pdf
work_keys_str_mv AT sturki aim2pcaerialimageto3dbuildingpointcloudreconstruction
AT sturki aim2pcaerialimageto3dbuildingpointcloudreconstruction
AT dpanangian aim2pcaerialimageto3dbuildingpointcloudreconstruction
AT hchaabounichouayakh aim2pcaerialimageto3dbuildingpointcloudreconstruction
AT kbittner aim2pcaerialimageto3dbuildingpointcloudreconstruction