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
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, ...
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...
Ethics of climate change : a normative account
Ethics of climate change : a normative account
Consider, for instance, you and your family have lived around a place where you enjoyed the flora and fauna of the land as well as the natural environment. Fishing and farming were...
Serial cultural heritage concept, values identification, and management : case study Angkor - Phimai cultural route
Serial cultural heritage concept, values identification, and management : case study Angkor - Phimai cultural route
Serial cultural heritage refers to groups of cultural heritage sites which are formed as series by significant cultural linkage. It is a category of cultural heritage which has pla...
A quantitative description of the spatial–temporal distribution and evolution pattern of world cultural heritage
A quantitative description of the spatial–temporal distribution and evolution pattern of world cultural heritage
Abstract
Depicting the temporal and spatial evolution pattern of global world cultural heritage systematically and finely is the basis of heritage recognition and...
Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting
Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting
Currently, single image inpainting has achieved promising results based on deep convolutional neural networks. However, inpainting on stereo images with missing regi...

