=Paper=
{{Paper
|id=Vol-3271/Paper17_CVCS2022
|storemode=property
|title=Virtual Cleaning of Artworks Usinga Deep Generative Network
|pdfUrl=https://ceur-ws.org/Vol-3271/Paper17_CVCS2022.pdf
|volume=Vol-3271
|authors=Morteza Maali Amiri,David W. Messinger
|dblpUrl=https://dblp.org/rec/conf/cvcs/AmiriM22
}}
==Virtual Cleaning of Artworks Usinga Deep Generative Network==
https://ceur-ws.org/Vol-3271/Paper17_CVCS2022.pdf
Virtual Cleaning of Artworks Using a Deep Generative
Network⋆
Morteza Maali Amiri1,*,† , David W Messinger1,†
1
Rochester Institute of Technology, Chester F. Carlson Center for Imaging Science, 54 Lomb Memorial Drive, Rochester,
NY 14623, USA
Abstract
It is well-known that the varnish applied to artwork yellows with time changing its appearance ac-
cordingly. Conservators are then sometimes prompted to physically clean the artwork in an attempt
to recover the original look of the work. At times, the conservators only partially clean the artwork
first. They then try to virtually clean the rest of the artwork to visualize the result of the cleaning before
physically cleaning the entire piece. There have been many different approaches that have been proposed
to virtually clean a partially cleaned artwork. All of them have some limitations, the low accuracy of
which is the main one. In this paper, a deep generative network is proposed to virtually clean a partially
cleaned artwork in the RGB domain. The proposed generative model consists of several up-sampling
and down-sampling convolution blocks and skip connections with a symmetric architecture. The loss
function is calculated using the part of the artwork that has been physically cleaned for which we have
access to both RGB images before and after cleaning. Therefore the network is able to clean the whole
artwork using only a small area of it that has already been physically cleaned. A Macbeth ColorChecker
and images of the Mona Lisa are used to test the approach and the results are compared with a recent
approach available in the literature which uses a Convolutional Neural Network (CNN). The results are
found to be acceptable given that the approach proposed herein has a potential to be applied in a real
situation and there is no need for a large training dataset, on which the CNN method relied on.
Keywords
Deep Generative Network, Virtual cleaning of artworks, Varnish removal
1. Introduction
Artworks are usually varnished for the purpose of protection. Although successful in their
main purpose, with time, this application can change the visual qualities of artworks [1, 2, 3, 4].
Therefore, physically removing the aged varnish in order to reestablish the original appearance
of the artwork becomes of great importance [5, 6]. There have been two major approaches to
clean artwork, namely, physical and virtual cleaning. In the physical approach, the conservator
physically removes the varnish layer using a solvent and gel system. These types of cleaning
are very time-consuming and can also be detrimental to the artwork [7, 8, 9]. Virtual cleaning,
The 11th Colour and Visual Computing Symposium 2022, Sep 8–9,2022, Gjøvik, Norway ⋆
Supported by Xerox chair at Rochester Institute of Technology.
*
Corresponding author.
†
Morteza Maali Amiri
$ mm2391@rit.edu (M. M. Amiri); dwmpci@rit.edu (D. W. Messinger)
0000-0002-0391-3310 (M. M. Amiri); 0000-0002-2273-9194 (D. W. Messinger)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
on the other hand, refers to the outcome of the physical approach using simulation. Virtual
cleaning could provide the conservator with the likely appearance of the cleaned artwork,
helping them to see if the physical cleaning is necessary and potentially guide their work.
Most of the studies done in the area of virtual cleaning are based on first cleaning a small
part of the painting physically. and they use an RGB image of the painting before and after
cleaning. Using that small part, for which they have data belonging to both cleaned and unclean
state, they attempt to virtually clean the entire painting producing a visualization of the cleaned
work. They typically do that through fitting some type of regression to the data obtained from
the small area before and after cleaning. They then apply the same regression model to the rest
of the painting which leads to the artwork being virtually cleaned [10, 11]. Papas and Pitas
(2000) stated that the RGB color space of the camera does not work well and they proposed to
use the CIELAB color space instead, asserting that CIELAB works better than RGB color space.
Virtually cleaning the Mona Lisa was another breakthrough in the field of virtual cleaning [12].
Having access to the classical paints used in 16th century Italy, the authors were able to make a
varnished and unvarnished color chart out of them. They were able to extract the relationship
between the varnished and unvarnished color chart enabling them to estimate the unvarnished
version of the Mona Lisa [12]. Palomero and Soriano (2011) developed the first neural network
approach trying to virtually clean artworks [13]. They also first cleaned a part of the artwork
and then trained a shallow network using that small part. They then used the same model to
clean the rest of the artwork [13]. Trumpy, et al. (2015) developed the first physics-based model
in order to virtually clean artworks [14] through making a few simplifying assumptions, such
as that a dark site on the painting is a “perfect” black that absorbs all incident light (perfect
meaning not grayish) and the varnish spectral reflectance is wavelength independent. Through
first finding the darkest and lightest part of the painting and cleaning them, they were able to
estimate the spectral transmittance of the varnish layer which would be used to estimate the
cleaned spectral reflectance of the entire painting [14]. Kirchner, et al. (2018) used Kubelka-
Munk trying to estimate the virtually cleaned artworks [15]. In order to do that, they first
characterized the varnish layer through cleaning the artworks at a few spots that appeared
white allowing them to compute the spectral transmittance of the varnish. Characterizing the
varnish layer enabled them to estimate the cleaned version of the whole painting [15]. Linhares,
et al. (2020) did a similar work as [15] through characterizing the varnish layer first. However,
they characterized the varnish layer through removing the whole varnish and measuring the
spectral reflectance of the painting before and after varnish removal [16]. The latest work in
the area of virtual cleaning of artworks belong to Maali Amiri and Messinger (2021) [17]. They
first developed a Convolutional Neural Network (CNN) model. The network was trained on
images of natural scenes and humans that were artificially yellowed mimicking the impact that
varnish has on the artwork visually. They were able to visualize the cleaned version of artworks
using their proposed CNN model in a very acceptable manner [17]. The methods proposed
until now suffer from a few limitations, namely, the requirement to specify the perfect black
and white regions on the painting, the need to have access to spectral data, generalizability of
the method to other works, and the need to have access to a large set of data for training.
In this work, we propose a Deep Generative Network (DGN) to virtually clean a partially
cleaned artwork. The generative model we use herein has been used in the area of remote sensing
for the purpose of denoising of the hyperspectral image and single image super-resolution
[18, 19]. The authors developed a convolutional generative network that was able to take in
a noise cube and output a super-resolved remotely sensed image. The network is deep and
symmetrical and has also borrowed the idea of skip connections from U-Net enabling it to
use residual information as best as possible. In this work, we have modified the network to
fit our purpose. Instead of feeding the network with a random noise image, we feed in the
RGB image of the uncleaned artwork. To be more specific, we have information of a small
area of the painting before and after cleaning. The RGB image of the artwork is first changed
into CIELAB, and the a*b* channels are used to train the network. The loss function, on the
other hand, is computed between the uncleaned and the corresponding cleaned area of the
artwork (the small area for which we have access to both cleaned and uncleaned data). The
model is tested on Macbeth ColorChecker and the Mona Lisa that are partially cleaned. The
results show that our approach here has done a better job compared to the model proposed
by [17] when it comes to the Mona Lisa but has done slightly worse when compared to [17]
for the Macbeth ColorChecker. Overall, the method proposed herein is more applicable to a
real situation where the conservator has no access to a large set of data with which to train the
model. Comparing our model to that of [17] seems fair as in their paper they showed that their
model had outperformed the only physics-based model proposed for artwork virtual cleaning
[14, 17].
This paper is laid out as follows: the next section will present the specifications of the data,
while the method will be explained in a more detailed manner along with the evaluation metrics
and experimental environment. After that, results are presented along with discussions in the
next section. Finally the conclusions are presented.
2. Methodology
In this section, the data used are explained and the proposed algorithm is described in detail.
2.1. Data
One of the datasets used to test the proposed method is the Macbeth ColorChecker spectral
reflectance data. The spectral reflectances were artificially yellowed using the same formula
suggested by [17] in the spectral domain. The artificially yellowed spectral reflectance mimics
the visual impact varnish has on the painting. So, due to the Macbeth ColorChecker having a
wide range of colors along with neutral patches, we use it as an initial test for our approach. The
Macbeth ColorChecker is simulated in a way that it is “varnished” with a layer of a particular
spectral reflectance and transmittance (generally speaking, varnish is yellow, and its spectral
reflectance and transmittance should represent that [14, 15]), as explained by [17]. The yellowed
spectral reflectances and the originals were converted into sRGB data afterwards. The Macbeth
ColorChecker was primarily used to assess the feasibility of the proposed methods before
application to a well-known work of art. Consequently, we apply the network to the Mona Lisa
to further test the network. The varnished and cleaned versions of the Mona Lisa are taken
from [12].
2.2. Deep Generative Network (Architecture and Application)
In this section, the Deep Generative Network (DGN) that has been developed in this work is
described. This method requires only a small area of the artwork to be cleaned. Then using the
data of both the cleaned and varnished conditions of the same area, the network learns how to
map from the uncleaned condition to the clean one. It then applies the same map to the rest of
the artwork resulting in a virtually cleaned artwork.
The idea behind a DGN is top learn the relationship 𝑥 = 𝑓𝜃 (𝑧), which maps an image 𝑧 to
another image 𝑥. This approach is used here to recover the virtually cleaned artwork from
the unclean one in the RGB color domain. The goal here is to generate image 𝑋, which is the
virtually cleaned image of the varnished artwork. Through feeding the varnished image 𝑍 into
the generator, image 𝑋 with this characteristic will be attained. 𝑍 is the RGB image of the
artwork before cleaning. As mentioned above, only a small area of the painting is cleaned and
we have the RGB image of that area for both cleaned and uncleaned conditions. Let us call the
area of the painting for which we have both the cleaned and uncleaned data 𝐴. The RGB image
of this area that is physically cleaned is called 𝐴𝑐 and the corresponding RGB image of this area
that belongs to 𝑍 (that is unclean) is 𝐴𝑢 . It makes sense that 𝐴𝑢 belongs to 𝑍 as 𝑍 is the RGB
image of the uncleaned artwork. When 𝑍 goes through the network, the part corresponding
to 𝐴𝑢 is taken out and the pixel-wise error between 𝐴𝑢 and 𝐴𝑐 is calculated to compute the
loss, which is then back-propagated to the generator, through which the parameters 𝜃 of the
mapping function are optimized. Fig. 1 shows the process described. It should be noted that
there is no training in a traditional sense using this approach. The error computed between the
𝐴𝑢 and 𝐴𝑐 is back propagated to the generator and the generator will clean the whole image
using this error coming from the loss function. This cleaning process is taken place step by step
at each epochs, until the network reaches the maximum number of epochs.
Through trial and error we come to know that the network works better in CIELAB color
space than in RGB. This improvement in the neural network performance by changing the color
space to CIELAB has been reported in the literature as well [11]. Therefore, we first convert
the RGB image, 𝑍, into the CIELAB color space. The L* channel is then set aside and the a*b*
channels, as input, go through two main modules of the network, consisting of several blocks
as follows:
(1)
1) The down-sampling block 𝑑(𝑖) : Each 𝑑(𝑖) is composed of convolutional layer 𝐶𝑑 (𝑖) also
performing the down-sampling operation through setting the stride 𝑆 = 2. After that, batch
normalization and the LeakyReLU activation layer are performed. The output is then fed into
(2)
the next convolutional layer 𝐶𝑑 (𝑖) with the same stride. Similar to the first convolutional
layer, this operation is followed by a batch normalization layer and the LeakyReLU activation
(1) (2)
function. 𝐶𝑑 (𝑖) and 𝐶𝑑 (𝑖) can be set to different kernel sizes and different numbers of filters
(1) (2) (1) (2)
shown as 𝑘𝑑 (𝑖), 𝑘𝑑 (𝑖), 𝑛𝑑 (𝑖) and 𝑛𝑑 (𝑖).
2) The up-sampling block 𝑢(𝑖) : Each 𝑢(𝑖) consists of a few stacked layers. Opposite to the
down-sampling blocks, batch normalization is the first layer. Afterwards, the first convolutional
(1)
layer 𝐶𝑢 (𝑖) with S = 1 and a batch normalization and LeakyReLU activation function are
(2)
used. The output is then fed into the next convolutional layer 𝐶𝑢 (𝑖). The output, after batch
normalization and non-linear activation, is input into the bilinear up-sampling layer with factor
Figure 1: The overall algorithm of the proposed deep generative network. It should be noted that the
generator actually takes in the error and based on that, it generates a new image, which would be the
virtually cleaned image. There is no training in the traditional sense here, and the generator only learns
to clean the whole image using the error it is computing based on the cleaned parts.
(1) (2)
2. 𝐶𝑢 (𝑖) and 𝐶𝑢 (𝑖), similar to the down-sampling block, can be set to different kernel sizes
(1) (2) (1) (2)
and different numbers of filters shown as 𝑘𝑢 (𝑖), 𝑘𝑢 (𝑖), 𝑛𝑢 (𝑖) and 𝑛𝑢 (𝑖), respectively.
The skip connection, shown as 𝑠(𝑖) , is also utilized to connect the down-sampled data to the
up-sampled data (the up-sampling and down-sampling blocks are symmetrical), so the residual
Figure 2: The architecture of the work along with how the input and output are processed.
information can be fully employed. 𝑜(0) denotes the output block. It is indeed the up-sampling
block that is modified so that the up-sampling layer is superseded with one convolutional layer
which is followed by one Sigmoid activation layer.
The network has an hourglass architecture as shown in Fig. 2. Each down-sampling and
up-sampling sections are comprised of 5 blocks and 5 skip connections. The filter size is 3 × 3
in the up-sampling and down-sampling blocks but it is 1 × 1 in the last convolutional layer.
There are 128 filters in the convolutional layers in the down-sampling and up-sampling blocks
and there are only 2 (to be equal to the a*b* channels) filters in the last convolutional layers. As
it was mentioned, only a*b* channels of the image 𝑍 are input into the network. The output
from the network is also the a*b* of the image 𝑋. This output will be combined with the L*
channel of the image 𝑍 that was first set aside, constructing the CIELAB image of output 𝑋.
The CIELAB image is then converted back into RGB image following standard formulae for
sRGB.
As mentioned, the input to the network is the a*b* image of the uncleaned artwork 𝑍 and
the generated image is 𝑋. The cost function is defined as the pixel-wise difference between
𝐴𝑢 and 𝐴𝑐 . 𝐴𝑢 belongs to 𝑍 and therefore, it changes in each iteration. Consequently, the cost
function is given as
𝑚𝑖𝑛‖𝐴𝑢 − 𝐴𝑐‖2 (1)
It should be noted that the input to the model should be replaced with the output of the model
after each iteration. The overall algorithm is shown in Algorithm 1.
2.3. Evaluation Metrics and Experimental Environment
Visualization of the results, per-pixel spectral Euclidean Distance (ED) and Spectral Angle (SA),
between the original (cleaned) image and the virtually cleaned image, are the metrics used in this
work for accuracy evaluation[20]. The color space used is RGB and each pixel is considered a
vector in this space, with the vector tip located at a particular point in the color space according
to the RGB values. The spectral Euclidean distance is obtained through calculating the Euclidean
distance between two pixels in that color space. The spectral angle is calculated between two
Algorithm 1 Deep Generative Network Algorithm
Procedure: Virtual Cleaning (𝐴𝑐 )
Input: a*b* image of the uncleaned artwork 𝑍
while epoch < max_epoch do
𝑋 = 𝑀 𝑜𝑑𝑒𝑙(𝑍) (Model here stands for the deep generative model.)
𝐴𝑢 = 𝑋 (The part of the 𝑋 corresponding to 𝐴𝑐 is taken out)
𝑚𝑖𝑛‖𝐴𝑢 − 𝐴𝑐 ‖2
𝑍 = 𝑋 (replace the input with the output of the model in each iteration)
end while
Return 𝑋
End Procedure
vectors and is reported in radians in the range [0, 3.142], defined as
(︂ )︂
−1 t𝑘 · r𝑘
𝑆𝐴𝑘 = 𝑐𝑜𝑠 (2)
|t𝑘 ||rk |
where 𝑘 denotes the 𝑘 𝑡ℎ pixel, t𝑘 and r𝑘 denote the two pixels belonging to the test and reference
images, and 𝑆𝐴𝑘 denotes the spectral angle between these two pixels.
Python 3.9.7 |Anaconda, Inc. is used as a base coding environment for the DGN algorithm.
More specifically, the DGN codes were written and run in the TensorFlow environment, which
was installed onto the Anaconda. In terms of hardware, the programs are run on a GPU
(NVIDIA GeForce MX350). The training of the DGN is performed using only one image and is
consequently referred to as an unsupervised learning method [18]. As mentioned before, only
a small area of the image is used to compute the loss function, and the same loss is then used for
the whole image to virtually clean it. 1500 epochs are used to train the model. MATLAB R2022a,
the package of mathematical software was also used for evaluation computations, making the
Macbeth ColorChecker and yellowing it.
3. Results and Discussions
In this section, the results of applying DGN to virtually clean the Macbeth ColorChecker and
the Mona Lisa are presented and examined. First, we consider the Macbeth ColorChecker.
The Macbeth ColorChecker was simulated as varnished and unvarnished and is used to test
the approach, similarly to previous work by [17]. The Macbeth ColorChecker has 24 different
color patches, including a range of neutral samples. As mentioned, the DGN needs only a small
area of the painting to be physically cleaned and then, using that small part to learn the transfer
function describing the varnish effect, the whole painting is virtually cleaned. Given that the
Macbeth ColorChecker has different color patches, we empirically identified that the number of
patches necessary to be physically cleaned is at least three. Therefore, we applied the method,
using the following combination of three patches: a) red, green and blue, b) black and white
and a neutral patch, and c) all of the neutral patches, i.e., six neutral patches that exist on the
standard Macbeth ColorChecker. The combination in c obviously contains more than three
patches, but is presented as an alternate approach to training the network for testing. The results
are visually compared to the method proposed by [17], as shown in Fig. 3 and quantitatively
compared in Table 1.
Figure 3: a) all neutral patches, b) black and white and a neutral patch, c) CNN output, d) original
Macbeth, e) red, green and blue patches and f) unclean (i.e., yellow) Macbeth.
We observe that the DGN has done an acceptable job compared to the CNN proposed by [17],
even though the number of training samples required by the DGN is significantly smaller that
that of t he CNN. To have a better understanding of the results, Table 1 shows the quantitative
results in terms of the mean values of ED and SA for the whole ColorChecker. These metrics
are computed between the virtually cleaned color chart and the original one.
Table 1
Euclidean distance and SA mean and standard deviation (SD) values between the original and virtually
cleaned Macbeth color chart.
Method Euclidean distance SA
Mean SD Mean SD
All neutral patches 0.06 0.022 0.06 0.021
Black, white and a neutral patch 0.056 0.026 0.062 0.024
Red, green and blue patches 0.074 0.042 0.070 0.034
CNN proposed by [17] 0.021 0.002 0.014 0.004
As it is observed from Table 1, the CNN model has done a slightly better job in terms of
cleaning the Macbeth ColorChecker. This is not too concerning as the method proposed herein
is more practical than the CNN proposed by [17]. The DGN proposed herein only needs a small
area of the painting to be cleaned, while the CNN needs a significantly larger number of training
samples to work. While the end goal of each approach is the same, a virtually cleaned work of
art, the operational aspects of the two methods a significantly different.
Finally, we also applied the DGN to clean the Mona Lisa. The results are shown in Fig. 4.
Fig. 4 (c) shows the area of the painting that was used to compute the loss; in other words,
that area is used to train the network to go from the unclean to the clean version of the artwork.
As shown in Fig. 4 (e), the DGN has again done a visually acceptable job of cleaning the artwork,
considering that the area of the painting used to train the network is fairly small. The ED and
Figure 4: a) Unclean Mona Lisa, b) original clean Mona Lisa, c) The area of Mona Lisa that is assumed to
be physically cleaned, d) virtually cleaned using CNN proposed by [17], e) virtually cleaned using DGN.
SA are also computed between the original clean Mona Lisa and the virtually cleaned one. The
results are both visualized (Fig. 5) and reported in terms of the mean values across the whole
image (Table 2). The visualization of the ED and SA values show specific areas of the work
that are not well cleaned (note that in Figure 5 all four results are normalized to 1). To better
understand the absolute performance, the mean values of the ED and SA are also reported
which clarifies which method has outperformed the other. As it is observed from Fig. 5, the
CNN has not done a good job especially predicting the cleaned color of the sky, and overall the
error is higher and more widespread in the CNN.
We see from Table 2, the proposed method here has surprisingly outperformed the CNN
proposed by [17]. It is surprising as the CNN outperformed our proposed method when the
Macbeth ColorChecker was the object of interest, but the results here are the opposite in the
case of the Mona Lisa. This could be because of the richness of the colors and structural features
Figure 5: a) ED calculated between the original clean Mona Lisa and the virtually cleaned one using
CNN, b) ED calculated between the original clean Mona Lisa and the virtually cleaned one using DGN,
c) SA calculated between the original clean Mona Lisa and the virtually cleaned one using CNN, d) SA
calculated between the original clean Mona Lisa and the virtually cleaned one using DGN.
Table 2
Euclidean distance and SA mean and standard deviation (SD) values between the original and virtually
cleaned Mona Lisa.
Method Euclidean distance SA
Mean SD Mean SD
DGN 0.0167 0.0015 0.1045 0.0139
CNN [17] 0.0371 0.0024 0.1489 0.0209
that are present in the Mona Lisa, as opposed to the Macbeth ColorChecker, which is a simple
color chart. This would also confirm that the method proposed herein is more practical than
CNN, as asserted above. The method proposed herein has a potential of being applied to a wider
type of artworks compared to the CNN, which requires a large set of training data with content
similar to the artwork itself.
It is important to note that the small area chosen in the artwork should be a representative of
all the features and material present on the painting. Looking at Figure 4 (c), one could see that
the small area contains a small part of the sky, human eye and skin, and her dress. This will
strengthen the performance of the DGN. To examine this point further, another experiment
is performed in which, the small area varies from what has been chosen in Figure 4 (c). The
new small area only comprises the person (part of her face, her dress, her hair and her skin)
as shown in Fig. 6. In this Figure, the top row shows the results of Figs 4 and 5 combined in
the case of the DGN and the bottom row shows the results of the DGN when a different and
smaller area is chosen.
Figure 6: First experiment: a) SA calculated between the original clean Mona Lisa and the virtually
cleaned one using DGN, b) ED calculated between the original clean Mona Lisa and the virtually cleaned
one using DGN, c) virtually cleaned using DGN, d) The area of Mona Lisa that is assumed to be physically
cleaned. Second experiment: e) SA calculated between the original clean Mona Lisa and the virtually
cleaned one using DGN, f) ED calculated between the original clean Mona Lisa and the virtually cleaned
one using DGN, g) virtually cleaned using DGN, h) The area of Mona Lisa that is assumed to be physically
cleaned.
As seen from the bottom row of Fig. 6, the sky and everything around the person, has not been
cleaned as well as the top row where the area chosen is a better representative of everything in
the image. It is also worthwhile noting that the DGN has not done terribly, however, with a
more thorough area, it could lead to a better result.
4. Conclusions
In this work, we developed a Deep Generative Network (DGN) to tackle the problem of virtual
cleaning of artwork for visualization. We compared our method to the latest method in this
area which used a Convolutional Neural Network (CNN). We used the Macbeth ColorChecker
and the Mona Lisa to test our method. We found that the proposed model did not outperform
the CNN in the case of the Macbeth ColorChecker, but it did outperform the CNN in the case of
the Mona Lisa. This shows the high potential of the work proposed herein to be applied in the
real case and to a wider range of artworks. The method proposed herein could potentially help
the conservators with seeing how a painting would look if it were to be physically cleaned, or
aid them in choosing from different options they have for a physical cleaning and so forth.
5. Acknowledgments
This research was funded by the Xerox Chair in Imaging Science in the Chester F. Carson Center
for Imaging Science at the Rochester Institute of Technology.
References
[1] S. Constantin, The barbizon painters: a guide to their suppliers, Studies in conservation
46 (2001) 49–67.
[2] A. Callen, The unvarnished truth: Mattness,’primitivism’and modernity in french painting,
c. 1870-1907, The Burlington Magazine 136 (1994) 738–746.
[3] R. Bruce-Gardner, G. Hedley, C. Villers, Impressionist and post-impressionist masterpieces:
The courtauld collection, 1987.
[4] M. Watson, A. Burnstock, An evaluation of color change in nineteenth-century grounds
on canvas upon varnishing and varnish removal, in: New Insights into the Cleaning of
Paintings: Proceedings from the Cleaning 2010 International Conference, Universidad
Politecnica de Valencia and Museum Conservation Institute, Smithsonian Institution, 2013.
[5] L. Baij, J. Hermans, B. Ormsby, P. Noble, P. Iedema, K. Keune, A review of solvent action
on oil paint, Heritage Science 8 (2020) 1–23.
[6] S. Prati, F. Volpi, R. Fontana, P. Galletti, L. Giorgini, R. Mazzeo, L. Mazzocchetti, C. Samorì,
G. Sciutto, E. Tagliavini, Sustainability in art conservation: a novel bio-based organogel
for the cleaning of water sensitive works of art, Pure and Applied Chemistry 90 (2018)
239–251.
[7] E. Al-Emam, H. Soenen, J. Caen, K. Janssens, Characterization of polyvinyl alcohol-
borax/agarose (pva-b/ag) double network hydrogel utilized for the cleaning of works of
art, Heritage Science 8 (2020) 1–14.
[8] M. El-Gohary, Experimental tests used for treatment of red weathering crusts in disinte-
grated granite–egypt, Journal of cultural heritage 10 (2009) 471–479.
[9] D. Gulotta, D. Saviello, F. Gherardi, L. Toniolo, M. Anzani, A. Rabbolini, S. Goidanich,
Setup of a sustainable indoor cleaning methodology for the sculpted stone surfaces of the
duomo of milan, Heritage Science 2 (2014) 1–13.
[10] M. Barni, F. Bartolini, V. Cappellini, Image processing for virtual restoration of artworks,
IEEE multimedia 7 (2000) 34–37.
[11] M. Pappas, I. Pitas, Digital color restoration of old paintings, IEEE Transactions on image
processing 9 (2000) 291–294.
[12] M. Elias, P. Cotte, Multispectral camera and radiative transfer equation used to depict
leonardo’s sfumato in mona lisa, Applied optics 47 (2008) 2146–2154.
[13] C. M. T. Palomero, M. N. Soriano, Digital cleaning and “dirt” layer visualization of an oil
painting, Optics express 19 (2011) 21011–21017.
[14] G. Trumpy, D. Conover, L. Simonot, M. Thoury, M. Picollo, J. K. Delaney, Experimental
study on merits of virtual cleaning of paintings with aged varnish, Optics express 23 (2015)
33836–33848.
[15] E. Kirchner, I. van der Lans, F. Ligterink, E. Hendriks, J. Delaney, Digitally reconstructing
van gogh’s field with irises near arles. part 1: varnish, Color Research & Application 43
(2018) 150–157.
[16] J. Linhares, L. Cardeira, A. Bailão, R. Pastilha, S. Nascimento, Chromatic changes in
paintings of adriano de sousa lopes after the removal of aged varnish, Conservar Património
34 (2020) 50–64.
[17] M. Maali Amiri, D. W. Messinger, Virtual cleaning of works of art using deep convolutional
neural networks, Heritage Science 9 (2021) 1–19.
[18] J. M. Haut, R. Fernandez-Beltran, M. E. Paoletti, J. Plaza, A. Plaza, F. Pla, A new deep
generative network for unsupervised remote sensing single-image super-resolution, IEEE
Transactions on Geoscience and Remote sensing 56 (2018) 6792–6810.
[19] D. Ulyanov, A. Vedaldi, V. Lempitsky, Deep image prior, in: Proceedings of the IEEE
conference on computer vision and pattern recognition, 2018, pp. 9446–9454.
[20] B. Park, W. Windham, K. Lawrence, D. Smith, Contaminant classification of poultry
hyperspectral imagery using a spectral angle mapper algorithm, Biosystems Engineering
96 (2007) 323–333.