3D Reconstruction of Temples in the Special Region of Yogyakarta By Using Close-Range Photogrammetry

TL;DR

This paper presents a comprehensive 3D reconstruction method for temples in Yogyakarta using close-range photogrammetry, combining multiple algorithms to produce high-quality models comparable to commercial solutions.

Contribution

It introduces an integrated photogrammetry workflow with specific algorithms for feature detection, matching, and texturing, tailored for cultural heritage preservation.

Findings

Reconstructed 3D models matched quality of commercial software

Collected 1319 photos from five temples for reconstruction

Achieved high SSIM scores indicating accurate models

Abstract

Object reconstruction is one of the main problems in cultural heritage preservation. This problem is due to lack of data in documentation. Thus in this research we presented a method of 3D reconstruction using close-range photogrammetry. We collected 1319 photos from five temples in Yogyakarta. Using A-KAZE algorithm, keypoints of each image were obtained. Then we employed LIOP to create feature descriptor from it. After performing feature matching, L1RA was utilized to create sparse point clouds. In order to generate the geometry shape, MVS was used. Finally, FSSR and Large Scale Texturing were employed to deal with the surface and texture of the object. The quality of the reconstructed 3D model was measured by comparing the 3D images of the model with the original photos utilizing SSIM. The results showed that in terms of quality, our method was on par with other commercial method such as PhotoModeler and PhotoScan.