Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XLIX-B2-2026, pp. 1363-1370· 0 citations· 16 references
TL;DR
This work proposes a hybrid reconstruction pipeline, leveraging the strengths and benefits of each technique, which exploits the accurate geometry of photogrammetry in well-textured regions and the GS capabilities to improve completeness and visual aspect in areas featuring non-collaborative surfaces.
Abstract
Abstract. Among the image-based methods, photogrammetry is a consolidated 3D reconstruction technique able to provide highly accurate metric products, widely exploited in many domains. Photogrammetry is, however, conditioned by the characteristics of the captured scene, with good performance in well-textured areas and limits when non-collaborative surfaces, such as reflective or transparent, are present. In such cases, the photogrammetric reconstruction is often affected by noise, incomplete geometry and artifacts, reducing its final reconstruction quality. In recent years, different AI-based reconstruction methods have emerged as alternative (or complementary) 3D reconstruction and rendering solutions. In particular, 3D Gaussian Splatting (GS) has demonstrated impressive capabilities in rendering photorealistic scenes in challenging situations with high visual fidelity. However, its application in large-scale scenarios or when highly accurate 3D metric products are required is still limited, due to the high computational resources needed and the intrinsic optimization of GS methods for photometric rendering quality. To address these bottlenecks, this work proposes a hybrid reconstruction pipeline, leveraging the strengths and benefits of each technique. The method exploits the accurate geometry of photogrammetry in well-textured regions and the GS capabilities to improve completeness and visual aspect in areas featuring non-collaborative surfaces. A fusion strategy is proposed to combine the two results into a single 3D model, presenting examples from two aerial and one terrestrial dataset.
Three Gaussian splatting methods as implemented in the Postshot commercial software were tested and show that MILo shows very promising results in terms of detail reconstruction, while standard Gaussian splatting excels in visualisation but is still plagued by a high rate of noise especially when converted into a geometric point cloud form.
Sara Gonizzi Barsanti, D. Billi, E. Sommer et al.· The International Archives o...· 0 citations
Abstract. This paper presents a comparative analysis of traditional photogrammetric methods and 3D Gaussian Splatting (3DGS) technology in the digitisation of Cultural Heritage (CH). Two representative datasets, differing in scale and image acquisition conditions, were selected to systematically evaluate the performance of both methods in terms of visual quality, geometric accuracy, computational efficiency and stability. The results indicate that 3DGS significantly outperforms traditional photogrammetry methods in terms of rendering quality and real-time visualisation capabilities, generating more realistic and immersive visual effects. However, its geometric accuracy is generally slightly lower than that of traditional methods, a difference that is particularly pronounced in small-scale datasets or under low-resolution input conditions. Among the various implementation methods, Postshot and LichtFeld Studio demonstrated higher stability and robustness, whilst the original GraphDeco method exhibited greater sensitivity to data scale and parameter settings. Photogrammetry offers reliability in high-precision geometric reconstruction, whilst 3DGS demonstrates significant potential for complementing this with a high-fidelity visual experience. The research findings try to provide practical guidance for selecting 3D reconstruction methods across different cultural heritage application scenarios.
Xin-Chen Li, Alessio Martino, F. Chiabrando et al.· The International Archives o...· 0 citations
Physical inspections in various contexts (industrial, operational, medical, etc.) often require surface analysis, but how is it possible to review or improve past inspections retrospectively, even when the object under investigation is no longer available? Classical photogrammetry enables 3D reconstructions but often struggles with incomplete photo sets or noise. This study integrates photogrammetry with Gaussian Splatting, a recent technique enhancing visualisation via colour-based 3D rendering; virtual images obtained from Gaussian-Splatting renders enable the retrospective revisiting of photogrammetry-based reconstructions, improving their quality and accuracy. Two case studies in aerospace maintenance and medical imaging suggest that this approach can enhance
ex-post
surface inspections, allowing for a closer examination of details that were initially overlooked. The novelty of this contribution lies in the use of virtual renderings not only for visualisation purposes, but also as supplementary data to enrich 3D reconstruction, combining the visual strength of Gaussian Splatting with the geometric reliability of photogrammetry.
M. Trombini, D. Maisano, F. Franceschini· Scientific Reports· 0 citations
This work aims to guide future research toward robust, accurate, and certifiable 3D reconstruction systems suitable for engineering, industrial, and geospatial applications, by bridging the gap between classical photogrammetry and data-driven 3D vision.
Xin Wang, Tengfei Wang, M. Hillemann et al.· PFG – Journal of Photogramme...· 0 citations
Inspection activities on industrial assets, for instance in the aerospace or automotive industry, frequently pertain to the examination of the surface conditions of objects. Among the established techniques for surface assessment, photogrammetry has gained increasing relevance in manufacturing quality monitoring, due to its ability to provide high-fidelity 3D spatial data. However, during the photogrammetric reconstruction of a physical object, some regions may be reconstructed less accurately, for example due to an insufficient number of local photographic acquisitions; in such cases, additional photographs of these regions would be needed. This, however, requires the object to remain accessible and unchanged from the time of the initial acquisition; in practice, this condition is rarely met, as the object is often no longer accessible or is found in a different state. Therefore, photogrammetry is intrinsically tied to the acquisition moment, since it relies on images captured at a specific time and does not allow purpose-driven further inspection. This paper proposes a solution to this limitation of traditional photogrammetry, exploiting the concept of “3D scene”, defined as a high-fidelity digital representation of an object at a specific moment in time. Recent advances in radiance-field methods, particularly Gaussian Splatting (GS), enable the creation of fully navigable 3D
frozen-in-time
scenes, allowing for the extraction of digital images, i.e., renders, that can be integrated into the photogrammetric process to enhance reconstruction quality. The most significant advantage of GS-based scenes is that they are generated from exactly the same photographs used for the preliminary (and sometimes incomplete) photogrammetric reconstruction, without requiring any additional acquisitions. This combined use of photogrammetry and GS introduces the innovative paradigm of
back-in-time inspection
into manufacturing. This study addresses two main research questions: (i)
How can the combined use of photogrammetry and GS be employed for inspection tasks?
and (ii)
To what extent does GS improve reconstruction completeness and defect detectability?
A case study in the aerospace sector is proposed to demonstrate the effectiveness of this method.
M. Trombini, D. Maisano, F. Franceschini· The International Journal of...· 0 citations
3D Gaussian Splatting (3DGS) enables real-time rendering of photorealistic scene representations from multiview images and has potential as a visualization layer for digital twins. However, photorealistic appearance and image-level metrics alone do not establish practical suitability. We evaluate standard 3DGS on six real-world datasets: wall, forest, piled-pier underside, steel-girder bridge, asphalt pavement, and outdoor sculpture. The framework combines held-out test-view metrics (PSNR, SSIM, and LPIPS), spatial error maps, region-of-interest (ROI) inspection, computational records, scale–opacity grouping, and Gaussian-to-MVS distance analysis. In the wall case study, extending adaptive density control from 7000 to 30,000 iterations nearly doubled Gaussian count and model size and increased training time by about 50%, with only modest test-view improvements. Scale–opacity classes did not reliably distinguish high- from low-error regions. Gaussian-to-MVS distance was more strongly associated with scale than learned opacity, and median local errors generally increased with distance, although distributions overlapped substantially. Across datasets, major structures were generally reproduced well, whereas sparse foliage, low-contrast repetitive textures, fine surface details, and distant background objects required ROI-level verification. The best test-view performance reached 37.11 dB PSNR, 0.952 SSIM, and 0.193 LPIPS. Practical evaluation should consider global quality together with local, computational, and geometric characteristics.
Tomohiro Mizoguchi· Italian National Conference...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
