Digital Heritage Reconstruction Using Super-resolution and Inpainting

Padalkar, Milind G.; Joshi, Manjunath V.; Khatri, Nilay L.

doi:10.2200/s00740ed1v01y201611vcp026

Cited by 3 publications

(3 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sonnemann et al [22] conducted a project named "The Angkorian temples project" one of the world's largest religious monuments located in Cambodia in which, thousands of 3D models of heritage structures were reconstructed by using aerial imagery. Padalkar et al [23] present various techniques for automatically detecting and inpainting damaged regions in heritage monuments to obtained high-quality images to design different virtual reality systems. The authors also explained the worrisome current condition of various heritage sites around the world, which are damaged by natural causes and visitors.…”

Section: Literature Reviewmentioning

confidence: 99%

Deformable Object Removal via Exemplar-Based Algorithm for 3d Model of Heritage Structures

Buatik¹

2021

GEOMATE

View full text Add to dashboard Cite

Heritage structures are important for tourism and for learning about nations' history. Historical sites around the world are in damaged conditions due to various factors from the environment, man-made activities or natural calamities. To ensure safety and avoid further deterioration, digital reconstruction of heritage sites can be used to create 3D virtual models of these structures for archiving and for inspection purpose. This paper presents a technique to reconstruct a high-quality image-based 3D model of a heritage structure. An exemplar-based inpainting algorithm was used for removing deformable obstacles such as trees in 2D images since such obstacles are unwanted in a final 3D model. They also create noise in the 3D modeling process, which makes the final 3D model less accurate. In this paper, an inpainting algorithm is applied to generate implied texture to fill holes that occurred from removing objects so that the generated 3D model does not contain any hole and becomes watertight. The modified exemplar-based inpainting algorithm was implemented on 2D images to remove unwanted objects, and then the image-based 3D modeling technique was applied to create a 3D model that did not contain any unwanted objects. The results show that the final 3D model is more accurate when applied the object removal process and the model provides better visualization for heritage structures.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Deformable Object Removal via Exemplar-Based Algorithm for 3d Model of Heritage Structures

Buatik¹

2021

GEOMATE

View full text Add to dashboard Cite

show abstract

“…Nevertheless, SRR algorithm reinforces the heritage data preservation not only for today's use but also for further use. In literature, various SRR methods [3,4] have been proposed for the preservation of digital heritage images. In [3], Padalkar et al utilized self-learning based SRR algorithm and auto-inpainting techniques for the resolution enhancement and crack repairing of heritage images.…”

Section: Introductionmentioning

confidence: 99%

“…In literature, various SRR methods [3,4] have been proposed for the preservation of digital heritage images. In [3], Padalkar et al utilized self-learning based SRR algorithm and auto-inpainting techniques for the resolution enhancement and crack repairing of heritage images. In [4], Madhu et al proposed CNN based method for digital heritage image reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Network for Heritage Image Super Resolution

Nayak

Balabantaray

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

In this paper we have proposed Generative Adversarial Network (GAN) based Super resolution reconstruction (SRR) method for the estimation of high resolution (HR) heritage images. The proposed SRR method via the GAN model (SRRGAN) is modeled as a min-max optimization process by integrating some new loss functions which will enable to maintain spatial and textural homogeneity in the estimated HR images. Initially, we have divided the input test image into Textured and Non-Textured patches based on their inherent characteristic followed by the optimization of the GAN model via loss functions lossTeXP and lossNonT eXP respectively to yield textured and non-textured patches of the HR image. Loss function lossTeXP helps to preserve realistic and diverse textural content of heritage images along multi-scale and multiorientations. Whereas, lossNonT eXP efficiently preserves the complete high-frequency map of the heritage images. Consequently, the estimated HR images preserve sufficient image details with realistic textural content and reduced artifacts compared with the existing state-of-the-art SRR methods.

show abstract

Automatic Detection and Inpainting of Defaced Regions and Cracks in Heritage Monuments

Padalkar

Joshi

2017

Digital Hampi: Preserving Indian Cultural Heritage

View full text Add to dashboard Cite

Digital Heritage Reconstruction Using Super-resolution and Inpainting

Cited by 3 publications

References 115 publications

Deformable Object Removal via Exemplar-Based Algorithm for 3d Model of Heritage Structures

Deformable Object Removal via Exemplar-Based Algorithm for 3d Model of Heritage Structures

Generative Adversarial Network for Heritage Image Super Resolution

Automatic Detection and Inpainting of Defaced Regions and Cracks in Heritage Monuments

Contact Info

Product

Resources

About