Restoration of artwork using deep neural networks

Gupta, Varun; Sambyal, Nitigya; Sharma, Akhil; Kumar, Praveen

doi:10.1007/s12530-019-09303-7

Cited by 20 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The digital process enables precise reproductions of cultural goods (e.g. Gupta, Sharma andKumar 2019, Barbieri, Fabio andMuzzupappa 2017). It has been empirically analyzed whether viewers are able to differentiate between originals and reproductions.…”

Section: A Radical Proposalmentioning

confidence: 99%

Copies and Random Decision: a proposal to peacefully solve the conflict around looted art

Frey¹

2021

SoS

View full text Add to dashboard Cite

show abstract

Section: A Radical Proposalmentioning

confidence: 99%

Copies and Random Decision: a proposal to peacefully solve the conflict around looted art

Frey¹

2021

SoS

View full text Add to dashboard Cite

show abstract

“…The application of image completion and inpainting to fine art and painting reconstruction is still an incipient field, with very few examples to date like (Zeng et al, 2019) reconstructing Van Gogh's degraded painting or (Gupta et al, 2019) for restoration in digital art. In these works, the aim is not to create new content to fill-in missing sections of an image, but to restore existing content, degraded sections or lines.…”

Section: Related Workmentioning

confidence: 99%

Image Inpainting Applied to Art: Completing Escher’s Print Gallery

Orozco¹,

Buemi²,

Berllés³

2021

LatinX in AI at International Conference on Machine Learning 2021

View full text Add to dashboard Cite

Action recognition in videos is currently a topic of interest in the area of computer vision, due to potential applications such as: multimedia indexing, surveillance in public spaces, among others. In this work we propose an attention mechanism adapted to a CNN–LSTM base architecture. To carry out the training and testing phases, we used the HMDB-51 and UCF-101 datasets. We evaluate the performance of our system using accuracy as the evaluation metric, obtaining 57.3% and 90.4% for HMDB-51 and UCF-101 respectively.

show abstract

“…The method automatically repairs Greek temples based on a rendering of the ruins obtained from the 3D model. Gupta et al [13] proposed a hybrid model that employs R-CNN-based automatic mask generation and image inpainting with partial convolution and automatic mask update using U-Net architecture. The results show that the proposed method is quite effective in the virtual restoration of digitized artworks.…”

Section: Introductionmentioning

confidence: 99%

Enhancement and Restoration of Scratched Murals Based on Hyperspectral Imaging—A Case Study of Murals in the Baoguang Hall of Qutan Temple, Qinghai, China

Sun

Hou

Lyu

et al. 2022

Sensors

View full text Add to dashboard Cite

Environmental changes and human activities have caused serious degradation of murals around the world. Scratches are one of the most common issues in these damaged murals. We propose a new method for virtually enhancing and removing scratches from murals; which can provide an auxiliary reference and support for actual restoration. First, principal component analysis (PCA) was performed on the hyperspectral data of a mural after reflectance correction, and high-pass filtering was performed on the selected first principal component image. Principal component fusion was used to replace the original first principal component with a high-pass filtered first principal component image, which was then inverse PCA transformed with the other original principal component images to obtain an enhanced hyperspectral image. The linear information in the mural was therefore enhanced, and the differences between the scratches and background improved. Second, the enhanced hyperspectral image of the mural was synthesized as a true colour image and converted to the HSV colour space. The light brightness component of the image was estimated using the multi-scale Gaussian function and corrected with a 2D gamma function, thus solving the problem of localised darkness in the murals. Finally, the enhanced mural images were applied as input to the triplet domain translation network pretrained model. The local branches in the translation network perform overall noise smoothing and colour recovery of the mural, while the partial nonlocal block is used to extract the information from the scratches. The mapping process was learned in the hidden space for virtual removal of the scratches. In addition, we added a Butterworth high-pass filter at the end of the network to generate the final restoration result of the mural with a clearer visual effect and richer high-frequency information. We verified and validated these methods for murals in the Baoguang Hall of Qutan Temple. The results show that the proposed method outperforms the restoration results of the total variation (TV) model, curvature-driven diffusion (CDD) model, and Criminisi algorithm. Moreover, the proposed combined method produces better recovery results and improves the visual richness, readability, and artistic expression of the murals compared with direct recovery using a triple domain translation network.

show abstract

Restoration of artwork using deep neural networks

Cited by 20 publications

References 14 publications

Copies and Random Decision: a proposal to peacefully solve the conflict around looted art

Copies and Random Decision: a proposal to peacefully solve the conflict around looted art

Image Inpainting Applied to Art: Completing Escher’s Print Gallery

Enhancement and Restoration of Scratched Murals Based on Hyperspectral Imaging—A Case Study of Murals in the Baoguang Hall of Qutan Temple, Qinghai, China

Contact Info

Product

Resources

About