Javascript must be enabled to continue!
Region of Interest-Based 3D Inpainting of Cultural Heritage Artifacts
View through CrossRef
In this article, we address the problem of 3D inpainting using an exemplar-based method for point clouds. 3D inpainting is a process of filling holes or missing regions in the reconstructed 3D models. Typically, inpainting methods addressed in the literature fill missing regions due to occlusions or inaccurate scanning of 3D models. However, we focus on scenarios involving naturally existing damaged models, which are partly broken or incomplete in the artifacts at cultural heritage sites. We propose an exemplar-based inpainting technique using the region of interest (ROI)-based method to inpaint the missing regions of the damaged model. The ROI of a 3D model is represented as a set of Riemannian manifolds, and metric tensor and Christoffel symbols are used as geometric features to capture the inherent geometry. We then decompose the ROI into basic shape regions, namely, spherical, conical, and cylindrical components, and identify the best-fit match for inpainting. Instead of using a single similar exemplar for inpainting, we select the most relevant best-fit region to fill the missing region from the basic shape regions library obtained fromnsimilar exemplars. We demonstrate the performance of the proposed inpainting method on artifacts at UNESCO World Heritage site Hampi temples, India with varying complexities and sizes for both synthetically generated holes and real missing regions in 3D objects.
Association for Computing Machinery (ACM)
Title: Region of Interest-Based 3D Inpainting of Cultural Heritage Artifacts
Description:
In this article, we address the problem of 3D inpainting using an exemplar-based method for point clouds.
3D inpainting is a process of filling holes or missing regions in the reconstructed 3D models.
Typically, inpainting methods addressed in the literature fill missing regions due to occlusions or inaccurate scanning of 3D models.
However, we focus on scenarios involving naturally existing damaged models, which are partly broken or incomplete in the artifacts at cultural heritage sites.
We propose an exemplar-based inpainting technique using the region of interest (ROI)-based method to inpaint the missing regions of the damaged model.
The ROI of a 3D model is represented as a set of Riemannian manifolds, and metric tensor and Christoffel symbols are used as geometric features to capture the inherent geometry.
We then decompose the ROI into basic shape regions, namely, spherical, conical, and cylindrical components, and identify the best-fit match for inpainting.
Instead of using a single similar exemplar for inpainting, we select the most relevant best-fit region to fill the missing region from the basic shape regions library obtained fromnsimilar exemplars.
We demonstrate the performance of the proposed inpainting method on artifacts at UNESCO World Heritage site Hampi temples, India with varying complexities and sizes for both synthetically generated holes and real missing regions in 3D objects.
Related Results
The challenges and key issues in the promotion and conservation of cultural heritage
The challenges and key issues in the promotion and conservation of cultural heritage
Governmental policies and international agreements, such as the UNESCO World Heritage Convention, are evaluated to determine their impact on cultural heritage conservation. The stu...
Identification, documentation and promotion of cultural heritage: problems and prospects in the Indian context
Identification, documentation and promotion of cultural heritage: problems and prospects in the Indian context
PurposeThe purpose of this paper is to overview the current state of affairs of the Indian heritage treasures, which are being identified, restored, preserved and promoted by vario...
Image Inpainting Research Based on Deep Learning
Image Inpainting Research Based on Deep Learning
Abstract
With the rapid development of computer technology, image inpainting has become a research hotspot in the field of deep learning. Image inpainting belongs...
Ancient mural inpainting via structure information guided two-branch model
Ancient mural inpainting via structure information guided two-branch model
AbstractAncient murals are important cultural heritages for our exploration of ancient civilizations and are of great research value. Due to long-time exposure to the environment, ...
The Bronze Artifacts of Tall Jalul, Jordan
The Bronze Artifacts of Tall Jalul, Jordan
Background It is quite common at excavation sites throughout the Near East to uncover the remains of metallic artifacts, though the practice of investigating these objects has flu...
Културното наследство като ресурс за местно развитие
Културното наследство като ресурс за местно развитие
Статията има за цел да разкрие социалноикономическите ползи от един подход за създаване и социализиране на историческия комплекс Цари Мали град в село Белчин. Данните са получени о...
Diversity-Generated Image Inpainting with Style Extraction
Diversity-Generated Image Inpainting with Style Extraction
The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. This type of method generally atte...
MD-GAN: Multi-Scale Diversity GAN for Large Masks Inpainting
MD-GAN: Multi-Scale Diversity GAN for Large Masks Inpainting
Image inpainting approaches have made considerable progress with the assistance of generative adversarial networks (GANs) recently. However, current inpainting methods are incompet...

