ΕΛ EN
Home | People | Vlachos, Marinos
24
Scholarly Works
50%
OA Ratio
42%
Collaborative Ratio
Scholar

Vlachos, Marinos

Department of Civil Engineering and Geomatics

6
H-index (Scopus)
278
Scholar Citations

Scholarly Works

Research Output

Recent Publications

The Impact of a Deep Learning Self-Adaptive Colour Restoration Pipeline for Deep Underwater Images in 3D Reconstruction

Demesticha S., Vlachos M., Skarlatos D.
Publishing year: 2025
Conference paper
International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences ISPRS Archives, 2025, Volume 48, Issue 2/W10-2025
Scopus
Pages 309-315
Underwater photogrammetry is challenged by image degradation caused by water absorption and scattering, which negatively impacts feature detection and 3D reconstruction quality. This study aims to evaluate the effectiveness of a Feedforward Neural Network-based colour correction method designed to enhance underwater image quality, thereby improving feature matching and subsequent 3D reconstruction processes. The proposed approach leverages deep learning to correct colour distortions without relying on physical models of underwater light propagation. Evaluation was performed using established feature detection algorithms, such as SIFT and SURF, applied to multiple underwater datasets capturing diverse imaging conditions. The goal is to determine whether neural network-based colour correction can increase the number of valid feature correspondences, improve sparse and dense point cloud generation, and ultimately support more accurate and robust 3D reconstructions. By integrating this correction method within a photogrammetric workflow, the study investigates the potential benefits and limitations of data-driven colour enhancement in underwater environments. The findings are intended to inform future development of hybrid approaches that combine physical modelling with deep learning, aiming to optimize both visual clarity and geometric fidelity in underwater mapping and documentation. This work contributes to advancing underwater photogrammetry by addressing critical challenges...

Self-Adaptive Colour Calibration of Deep Underwater Images Using FNN and SfM-MVS-Generated Depth Maps

Skarlatos, Dimitrios, Vlachos, Marinos
Publishing year: 2025
Thesis Repository
This PhD thesis addresses the challenge of colour attenuation in deep-water underwater images captured under artificial light. Initially, the research aimed to model and solve the issue through physical and mathematical approaches. However, due to challenges such as unknown environmental parameters and light reflection angles, the focus shifted to developing a more practical solution. The key innovation of this thesis is the creation of a Self-Adaptive Colour Calibration pipeline, which leverages Structure from Motion (SfM) and Multi-View Stereo (MVS) derived data, alongside DL techniques, to restore the true colours in underwater images without requiring detailed environmental knowledge. The proposed pipeline effectively corrects colour degradation in archival datasets, in the absence of spectral and environmental data, making it particularly suitable for archaeological underwater imaging and applications with limited resources. The results from the application of this methodology to datasets from two distinct underwater sites, Mazotos and Nissia, demonstrate its robustness and adaptability across varying conditions. A reference-based evaluation further confirmed the pipeline's ability to restore colours accurately, highlighting its potential for enhancing underwater imagery for archaeological and environmental studies.

Investigating the Accuracy of a 360° Camera for 3D Modeling in Confined Spaces: 360° Panorama vs 25-Rig Compared to TLS

G Kafataris, D Skarlatos, M Vlachos, A Agapiou
Publishing year: 2025
Journal article
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information …, 2025, 2025
Google Scholar
Pages 139-146
This study investigates photogrammetric solutions for surveying confined underground environments using a small and affordable 360° camera, applied in Tomb 4 at the UNESCO World Heritage Site, Tombs of the Kings in Paphos, Cyprus. Conducted within the framework of the ENGINEER project, this study evaluates the performance of a low-cost 360° 25-lens camera by comparing it to a terrestrial laser scanner (TLS) system used as a reference. The primary objective is to assess the suitability of the 360° camera for 3D documentation in restricted spaces, and to explore its potential application in conservation and restoration efforts at archaeological sites. Two different approaches were tested: using the camera images as 360° panoramic photos or as 25-photos rigid rig setup. The study analyses the accuracy of these methods by generating Point Clouds (PCs) and comparing them to the TLS reference dataset using metrics such as cloud-to-cloud distance, surface roughness, and PC density. In addition, a visual assessment was conducted.

Innovative Geospatial and Engineering Solutions for Cultural Heritage

Agapiou, Athos, Argyrou, Argyro, Gravanis, Elias, Hadjipetrou, Stylianos, Kafataris, Giorgos, Kyriakides, Nicholas, Kyriakidis, Phaedon, Lysandrou, Vasiliki, Michaelides, Kyriakos, Papakonstantinou, Apostolos, Skarlatos,...
Publishing year: 2025
Conference paper
International Conference TMM-CH – Transdisciplinary Multispectral Modelling and Cooperation for the Preservation of Cultural Heritage Addressing World Challenges, 2025
Repository
Cultural heritage is facing increasing vulnerability due to various threats, including natural disasters, human activities, and the escalating impacts of climate change. This study examines how geospatial technologies and engi-neering solutions can address these issues, emphasizing their potential to improve monitoring, protection, and preservation practices for cultural heritage sites. Ad-vanced geospatial technologies, such as non-contact geomatics sensors and struc-tural analysis techniques, offer further capabilities for heritage monitoring. These tools enable the development of early warning systems to proactively identify and mitigate risks to monuments before significant damage occurs. Such systems support timely interventions, reducing restoration costs and safeguarding the in-tegrity of heritage assets. By integrating advanced technologies with field-spe-cific requirements, this study provides an overview of effective resource alloca-tion. This paper highlights the objectives of two recently supported European and national ongoing projects of the Cyprus University of Technology (CUT), namely the “Geomatics and Civil Engineering Innovative Research on Heritage”, in short ENGINEER and the “Research and Innovation Knowledge Centre for Engineering in Heritage”, in short CONNECTING. Both projects’ tasks aim to fill research multidisciplinary gaps, push, and extend knowledge into new and innovative fields dealing with the monitoring, digitization, visualization, and preser...

Synopsis of activities of the ENGINEER project

Agapiou, Athos, Aktas, Y. D, Argyrou, Argyro, Barazzetti, L., Costa, A, Cuca, Branka, D’Ayala, D., Gravanis, Elias, Hadjipetrou, Stylianos, Kafataris, Giorgos, Kyriakides, Nicholas, Kyriakidis, Phaedon, Lysandrou, Vasili...
Publishing year: 2024
Conference paper
CAA-GR Conference, 2024
Repository

Self-adaptive colour calibration pipeline for deep underwater image restoration: a reference-based evaluation

M Vlachos, D Skarlatos, S Demesticha
Publishing year: 2024
Journal article
Virtual Archaeology Review, 2024, 2024
Google Scholar
Building upon our previous work on underwater (UW) image colour restoration, this paper advances the self-adaptive colour calibration (SACC) pipeline by introducing a systematic, reference-based quantitative evaluation. UW imagery is notoriously affected by wavelength-dependent light absorption, scattering, and colour attenuation, which distort the visual appearance of submerged objects and complicate scientific documentation. Traditional model-based correction techniques often depend on well-calibrated equipment or prior environmental data, while many artificial intelligence (AI)-driven approaches suffer from dataset bias and limited generalisability. Our work addresses these challenges by providing a flexible pipeline that restores colours without requiring extensive environmental metadata, thus making it particularly well-suited for archival and in-field datasets. New datasets acquired from the 18 th-century Nissia shipwreck site, located off Protaras in Cyprus, were employed to evaluate the pipeline under real-world excavation conditions. These datasets, captured with a rigid camera–strobe configuration, include reference regions with colour charts that provide reliable ‘ground-truth’(GT) values for objective comparison. Structure from Motion (SfM) and Multi-View Stereo (MVS) were used to derive depth maps, which, together with red-green-blue (RGB) values, were input to a Feedforward Neural Network (FNN). The network was trained using Adam and RMSprop optimisers, enabling...

24
Unique publications
50%
Open access (12 publications; 6 without information)
41.7%
With other institutions (10 publications; 8 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 6 7 0
H5-index 4 4 0
H10-index 6 7 0

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Civil Engineering and Geomatics