Conference Paper

Three-step Alignment Approach for Fitting a Normalized Mask of a Person Rotating in A-Pose or T-Pose Essential for 3D Reconstruction Based on 2D Images and CGI Derived Reference Target Pose

February 2021

DOI:10.5220/0010194102810292

Conference: 16th International Conference on Computer Vision Theory and Applications

Authors:

Gerald Zwettler

University of Applied Sciences Upper Austria

Christoph Praschl

University of Applied Sciences Upper Austria

David Baumgartner

University of Applied Sciences Upper Austria

mkrz lab

Show all 7 authorsHide

Imaging framework: An interoperable and extendable connector for image-related Java frameworks

Article

Dec 2021

The number of computer vision and image processing tasks has increased during the last years. Although Python is most of the time the first choice in this area, there are situations, where the utilization of another programming language such as Java should be preferred. For this reason, multiple Java based frameworks as e.g. OpenIMAJ, ND4J or multiple OpenCV wrappers are available. Unfortunately, these frameworks are not interoperable at all. In this work, the open-source Imaging Framework is introduced to solve exactly this problem. The project features a concept for combining multiple frameworks and provides an interoperable and extendable foundation to 9 image-related projects with 10 different image representations in Java.

ResearchGate has not been able to resolve any references for this publication.

Article

Full-text available

A review on 3D Gaussian splatting for sparse view reconstruction

April 2025 · Artificial Intelligence Review

Sparse view 3D reconstruction remains challenging due to inherent data scale limitations. Mainstream sparse view 3D reconstruction algorithms based on the NeRF framework struggle to balance generation quality and real-time performance. Recently, the advent of 3D Gaussian Splatting technology has demonstrated remarkable results, becoming increasingly prominent in 3D scene representation and ... [Show full abstract] reconstruction. Exploring the application of 3D Gaussian Splatting technology for sparse view 3D reconstruction represents a promising research avenue. Based on this, our paper provides a comprehensive review of current sparse view 3D reconstruction methods leveraging 3D Gaussian Splatting, with an emphasis on extracting effective reconstruction information from input images and utilizing these data to generate realistic scenes efficiently and reliably. We then provide a detailed discussion on how the algorithm addresses issues such as artifacts and scale ambiguous, which are common challenges in this field. In the subsequent sections, we present both quantitative and qualitative comparisons of various sparse-view 3D reconstruction methods, roughly demonstrating the advantages of sparse view 3D Gaussian splatting methods in terms of reconstruction quality and efficiency. Furthermore, we analyze the potential applications of sparse view 3D Gaussian splatting methods. Finally, we identify the challenges faced by sparse-view 3D Gaussian splatting reconstruction and suggest potential solutions. We hope that our analysis will provide valuable insights for future research efforts.

Article

Full-text available

Comparison of different 3D reconstruction software tools in preoperative modeling for cranio-maxillo...

April 2025 · Plastic and Aesthetic Research

Aim: This study evaluates the application of three-dimensional (3D) reconstruction technology in cranio-maxillofacial surgery, focusing on its ability to provide accurate anatomical data and essential support for preoperative planning. Methods: A comparative analysis was conducted using three commonly utilized 3D reconstruction software programs: 3D Slicer, ProPlan CMF, and Mimics. Each was ... [Show full abstract] assessed based on modeling accuracy, operational efficiency, and functional specialization. Data were collected and analyzed to identify the strengths and weaknesses of each software in different surgical contexts. Results: The findings demonstrate that all three software programs provide consistent modeling accuracy. However, significant differences were observed in terms of operational efficiency and functional specialization, which influence their applicability in various scenarios. Specifically, 3D Slicer excels in flexibility, ProPlan CMF in cranio-maxillofacial applications, and Mimics in precision and comprehensive functionality. Conclusion: 3D reconstruction technology has significant potential for optimizing preoperative planning in plastic surgery, especially in cranio-maxillofacial surgery. This study offers critical insights into the selection and optimization of 3D reconstruction software, paving the way for more effective and tailored surgical planning. Future research may focus on integrating AI-driven tools to enhance operational efficiency and broaden the application scope of 3D reconstruction in cranio-maxillofacial surgery.

Article

Full-text available

Generative adversarial networks for creating realistic training data for machine learning-based segm...

April 2025 · Machine Learning: Science and Technology

Accurate 3D reconstruction of the structure of nanomaterials is essential for studying their physical properties. Focused ion beam (FIB) tomography is a preferred method for creating 3D image stacks of micrometer-sized material volumes at nanometer resolution. To achieve valid 3D reconstructions from FIB tomography data, semantic segmentation of these images using machine learning-based methods ... [Show full abstract] is often beneficial. However, supervised machine learning requires a large amount of training data and ground truth, which is challenging because FIB tomography is a destructive technique. This motivates the use of synthetic training data generated with Monte Carlo simulations of the FIB tomography process. However, these simulations are computationally expensive, and the resulting synthetic imaging data still differs from real FIB tomography data in terms of the statistical distribution of various features. In this study, we propose a novel approach to overcome both problems, i.e. requiring high computation time and difference in data distribution, using generative adversarial networks.

Preprint

Full-text available

VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control

April 2025

Sparse-view 3D reconstruction is a fundamental yet challenging task in practical 3D reconstruction applications. Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction. Although these methods have made considerable advancements, they still show significant issues with overfitting. To reduce the overfitting, we ... [Show full abstract] introduce VGNC, a novel Validation-guided Gaussian Number Control (VGNC) approach based on generative novel view synthesis (NVS) models. To the best of our knowledge, this is the first attempt to alleviate the overfitting issue of sparse-view 3DGS with generative validation images. Specifically, we first introduce a validation image generation method based on a generative NVS model. We then propose a Gaussian number control strategy that utilizes generated validation images to determine the optimal Gaussian numbers, thereby reducing the issue of overfitting. We conducted detailed experiments on various sparse-view 3DGS baselines and datasets to evaluate the effectiveness of VGNC. Extensive experiments show that our approach not only reduces overfitting but also improves rendering quality on the test set while decreasing the number of Gaussian points. This reduction lowers storage demands and accelerates both training and rendering. The code will be released.