Article

Facade Style Mixing Using Artificial Intelligence for

Urban Infill
Ahmed Khairadeen Ali 1,2, * and One Jae Lee 2

1 Architectural Engineering Department, College of Engineering, University of Duhok, Duhok 42001, Iraq
2 Haenglim Architecture and Engineering Company, Seoul 431810, Republic of Korea; o.lee@haenglim.com
* Correspondence: ahmedshingaly@gmail.com

Abstract: Artificial intelligence and machine learning, in particular, have made rapid advances in
image processing. However, their incorporation into architectural design is still in its early stages
compared to other disciplines. Therefore, this paper addresses the development of an integrated
bottom–up digital design approach and describes a research framework for incorporating the deep
convolutional generative adversarial network (GAN) for early stage design exploration and the
generation of intricate and complex alternative facade designs for urban interiors. In this paper, a
novel facade design is proposed using the architectural style, size, scale, and openings of two adjacent
buildings as references to create a new building design in the same neighborhood for urban infill. This
newly created building contains the outline, style and shape of the two main buildings. A 2D building
design is generated as an image, where (1) neighboring buildings are imported as a reference using
the cell phone and (2) iFACADE decodes their spatial neighborhood. It is illustrated that iFACADE
will be useful for designers in the early design phase to create new facades in relation to existing
buildings in a short time, saving time and energy. Moreover, building owners can use iFACADE to
show their preferred architectural facade to their architects by mixing two building styles and creating
a new building. Therefore, it is presented that iFACADE can become a communication platform in
the early design phases between architects and builders. The initial results define a heuristic function
for generating abstract facade elements and sufficiently illustrate the desired functionality of the
prototype we developed.

Keywords: artificial intelligence; generative adversarial network; machine learning; computational

Citation: Ali, A.K.; Lee, O.J. Facade design; urban infill; facade design
Style Mixing Using Artificial
Intelligence for Urban Infill.
Architecture 2023, 3, 258–269.
https://doi.org/10.3390/ 1. Introduction
architecture3020015 Generally, building envelope configurations follow similar urban street configurations
Academic Editor: Avi Friedman dictated by city policy, including building height, width, color, openings, and the ratio of
open to built space [1]. Thus, when designing a new building in an existing neighborhood,
Received: 23 January 2023 architects typically look to the architecture of neighboring buildings to determine the mass
Revised: 26 March 2023
of the new building. The result is that each neighborhood uses an almost typical and
Accepted: 9 May 2023
repetitive module for all building massing, and the architect’s input in the design of new
Published: 11 May 2023
buildings is minimal due to city policy and existing neighboring buildings [2].
Conventional building design is an iterative process that is costly and time consuming:
(1) draw a bubble diagram of building zones and outlines; (2) create appropriate floor plans
Copyright: © 2023 by the authors.
and elevations and solicit input from clients; (3) return to the polished bubble diagram; and
Licensee MDPI, Basel, Switzerland. (4) iterate. Architects and their clients must also compromise on the quality of the design,
This article is an open access article given budget and time constraints. Therefore, there is a great demand in the architecture,
distributed under the terms and design and real estate industries for automated building mass generation techniques that
conditions of the Creative Commons have immense potential [3].
Attribution (CC BY) license (https:// Recently, there have been several experiments with generative approaches, variational
creativecommons.org/licenses/by/ autoencoders, in the field of computer vision (VAEs) [4], and generative adversarial net-
4.0/). works (GANs) [5]. In particular, GANs show important results in various computer vision

Architecture 2023, 3, 258–269. https://doi.org/10.3390/architecture3020015 https://www.mdpi.com/journal/architecture

Architecture 2023, 3 259

tasks, such as image generation [6–8], image conversion [9], super-resolution [10], and
text–image synthesis [11]. GANs have already been used for facade generation [8]. Pix2Pix
is based on conditional GAN [5]. By using conditional vectors, we can control the categories
or attributes of the generated images. Pix2Pix generates facade images with the condition
of a masked image containing predefined labels for each building element. However, both
GANs failed to generate facade images that look realistic.
In this paper, a novel facade design is proposed using the architectural form, height,
scale and openings of two adjacent buildings as a guide to construct a modern building
design with iFACADE in the same neighborhood for urban infill. The outline, style and type
of the superior buildings are used in this newly constructed building. As an image, a 2D
design for an urban infill building is created, where (1) neighboring buildings are imported
by cell phone for reference and (2) iFACADE decodes their spatial neighborhood. In the
urban neighborhood, a building design is created as an image and improved. The main
contributions of this work can be summarized as follows: (1) We propose the style-based
conditional generator to control the latent space. (2) Our proposed generator can generate
images reflecting each feature of condition information specifying multiple classes. (3) In
the experiments with a facade dataset, we show that the sounds in the style-based generator
indicate additional elements, such as building windows, walls, and outline information,
and that unseen types of building facades can be generated by mixing multiple types of
facades with mixed conditional weights.

2. Literature Review
2.1. Generative Adversarial Networks
Image-to-image conversion techniques aim to acquire a function of conditional image
creation that maps a source domain’s input image to a target domain’s corresponding
image. To solve diverse image-to-image conversion tasks, Isola et al. [12] first proposed
the use of conditional GANs. Their thesis has since been expanded to several scenarios:
unsupervised learning [7,8,13], multi-domain image synthesis [14], and conditional image
synthesis [15]. For their tasks, the above works have built dedicated architectures that
include training the generator network. In other hand, our research depends heavily on
utilizing the conditional StyleGAN generator.
Many articles have recently proposed different methods for studying semantic edits
of the latent code. A typical technique is to identify linear directions that lead to shifts
in a particular binary named attribute, such as human face young to old, or no-smile
to smile [6,14]. Abdal et al. [16] learn a translation between vectors in W+, changing a
collection of fixed named attributes. Finally, by modifying relevant components of the
latent code, Collins et al. [17] perform local semantic editing.

2.2. Feature Disentanglement

Some critical problems arise with the above approaches. First and foremost, the input
image must be invertible, i.e., there must exist a latent code that reconstructs the image.
However, the domain of the input image must usually be the same domain on which the
GAN was formed. For various image-to-image activities that convert between two separate
data domains, such as segmentation graphs, drawings, edges, etc., this limitation is a
significant constraint. By optimizing an extended space, such as W+, this limitation can be
circumvented [16,17]. In this case, however, the latent space does not contain rich semantics
for an ambiguous data range. For example, the latent code would not be semantically
relevant, even if the input sketches could be inverted when translating between sketches
and natural face images in W+ of a StyleGAN trained on faces. Second, the investment
in GAN remains overwhelming. Although direct encoding techniques have achieved
moderate performance in the restoration standard, optimization and hybrid techniques are
costly and take a long time to converge.
Architecture 2023, 3 260

2.3. Facade Image Generation

Based on this insight, the continuous image-to-image architecture of this research
directly encodes a given current image into the desired latent vector. Thus, one can directly
solve the image-to-image challenge while taking advantage of a pre-trained StyleGAN
without having to accept unnecessary constraints.
CycleGAN [7] transforms image to image but without changing the visual. This work
only transforms the style between the two types of images. In contrast, in this paper, by
setting several areas as constraints, we exploit the structure by fluctuating transformation
and type noise, including two or more types.

3. Methodology
In this paper, the current literature in the field of image-to-image translation is re-
viewed, and a model is proposed that can generate new building facades by mixing two
existing building facades in the neighborhood for urban infill. The methodology is divided
into two parts. The first part discusses the urban infill tool called iFACADE and the second
part discusses the development of the trained model.
The proposed framework generates an imaginary building from a reference building.
A neural network trained with elevations of real buildings can transform this into a realistic
building. If you then switch between different building views, it is possible to generate
different views of the same imaginary building. The iFACADE can generate new and
non-existent but realistic images by using conditional neural networks that remember a
specific set of features they have seen in the past: the same process we humans go through
when we dream.

3.1. Urban Infill System Architecture

Since each neighborhood has its own rules for a modular building style that all
buildings within the neighborhood should follow, most buildings have the same general
building characteristics, colors, window openings and style. Therefore, iFACADE was
developed to create a new building view based on the existing building styles of the
neighborhood.
The iFACADE system is divided into five main phases: (a) input of reference buildings
in the neighborhood, where two color 2D facade images of reference buildings (B1 and B2)
as shown in Figure 1b (iFACADE trained model) are required as the input and architectural
guidelines of the neighborhood are required as the resource test to help the architect
evaluate the generated facade correctly; (b) the use of iFACADE’s trained model to input
reference images, extract features, and generate a new 2D image using the trained model
for style blending; (c) the output of a B0 2D image containing the features of both reference
images as shown in Figure 1; (d) evaluations where the architect manually evaluates
the generated facade and checks if it is compatible with the architectural features of the
neighborhood and submits an evaluation report; and (e) the iFACADE team re-evaluates
the trained model and improves the system architecture depending on the feedback from
the architect and users.
The system is built in a cloud and a front–back-end website is developed to host the
trained models. It is important that the website allows users to interact from anywhere
by logging into it. Currently, the system has only one feature, which is the creation of
style-mix images. In the future, it could be expanded to provide more information about
the regulations of each neighborhood. The user submits an evaluation report, which helps
the iFACADE team to evaluate the iFACADE model, improve its system architecture, and
re-train it. In addition, user-uploaded images are added to and enhance the training dataset,
which will help the iFACADE team create better and more accurate facades in the future as
shown in Figure 1.
Architecture 2023, 3 261

Figure 1. The iFACADE system architecture.

3.2. Style Mixing Trained Model System Architecture

In this subsection, the architecture of the model trained by iFACADE and the methods
used to control the facade style are explained. Therefore, the main elements of the model
architecture are explained, including the generator, the discriminator, the style mixture, the
latent space control, and the dataset used to train the model.
In general, the iFACADE model consists of a generator that produces a fake facade
image as a function of a real image and a discriminator that determines whether the input
image is fake or real.

3.2.1. Conditional Style-Based Generator

In this subsection, we explain the model generator and custom adaptive instance
normalization (AdaIN) architecture. The generator used in iFACADE is a conditional style-
based neural network that uses transpose convolution to upscale input images. Compared
to the traditional StyleGAN [18], the iFACADE generator controls the latent space of
the conditional StyleGAN generator by inputting the conditional information (y) to the
mapping function ( f ) in the fully connected (FC) layer. This method is adopted from [18].
This research performed a nonlinear conversion of the latent vector z to conditional
style information into two scalers (ys and yb ), where s stands for scalar and b stands for
bias to control an adaptive instance normalization layer (AdaIN). The AdaIN operation is
defined as

y = (ys , yb ) = f (w) (1)

xi − µ ( x )
AdaIN( xi , y) = ys + yb (2)
σ( x)
where xi is a normalized instance that we apply AdalN to, y is a set of two scalars
(ys , yb ) that control the “style” of the generated image, and f (w) represents a learning
affine transformation.
In the proposed generator, the AdalN operation is normalized to map networks that
show various styles. The dimensions of feature map z are half of the conditional style value.
The objective function used in the StyleGAN of this research is adopted from [18] that uses
the hinge version of the standard adversarial loss [6], defined as
Architecture 2023, 3 262

L( Gˆ, D ) = Eq (y)[ Eq ( x |y)[max (0, 1 − D ( x, y))]] + Eq (y)[ E p (z)[max (0, 1 + D ( Gˆ(z, y), y))]] (3)

L( G, Dˆ) = − Eq (y)[ E p (z)[ Dˆ( G (z, y), y)]] (4)

where p(z) is the standard Gaussian distribution. The generator’s conditional mapping
function z is fed to multiple fully connected (FC) layers. The latent code of a traditional
StyleGAN generator is fed only the input layer (z) on the left. iFACADE adds additional
conditional information (y) to the StyleGAN generator (left). The conditional code (y) gives
more control on the style as depicted in Figure 2.

Figure 2. The latent code of a traditional StyleGAN generator is fed only the input layer (z) on the
left. iFACADE adds additional conditional information (y) to the StyleGAN generator (left). The
conditional code (y) gives more control on the style.

3.2.2. Conditional Discriminator

The discriminator is an unsupervised classifier that determines if the input image is
true or fake. The model architecture of discriminator used in iFACADE is adopted by a
projection discriminator proposed by [6]. Different from the approach of concatenating the
embedded conditional vectors into feature vectors, the projection discriminator integrates
conditional vectors.

3.2.3. Style Transfer

To further encourage the styles to localize, we employ mixing regularization, where a
given percentage of images are generated using two random latent codes instead of one
during training. It switches from one latent code to another at a randomly selected point in
Architecture 2023, 3 263

the synthesis network when producing such an image. To be specific, we run two latent
codes z1, z2 through the mapping network, and have the corresponding w1, w2 control
the styles so that w1 applies before the crossover point and w2 after it. This regularization
technique prevents the network from assuming that adjacent styles are correlated.
As a basis for our metric, we use a perception-based pairwise image distance that
is calculated as a weighted difference between two Visual Geometry Group from Oxford
(VGG16) [19] embeddings, where the weights are fit so that the metric agrees with human
perceptual similarity judgments. If we subdivide a latent space interpolation path into
linear segments, we can define the total perceptual length of this segmented path as the
sum of perceptual differences over each segment as reported by the image distance metric.
The average perceptual path length in latent space is Z over all possible endpoints.

4. Case Study
4.1. Model Training Dataset
This research trained a conditional generative adversarial network, using customized
StyleGAN [18] to reconstruct the facade images from the CMP dataset. It uses a total of
720 images of facade that were adopted from the Center for Machine Perception (CMP) [20],
eTraining for Interpreting Images of Man-Made Scenes (eTRIMS) [21] and EuroCity Persons
(ECP) datasets [22]. The CMP dataset contains 606 pairs of annotated and real images
of facade images. The images are from different international cities, but they share a
similar modern architecture style with minor detailed architectural style differences that are
neglected in this paper. We processed the images manually and chose the best 420 images
and erased the rest. The additional images were collected from the eTRIMS database,
which contained 60 facade images, and the Ecole Centrale Paris facade database. The
facade images collected were processed to 128 × 128 pixels with 3 channels, and divided to
80 percent training, 15 percent test and 5 percent validation. The facade images constraints
are the following 12 classes: facade, molding, cornice, pillar, window, door, sill, blind,
balcony, shop, decoration, and background.
To increase the training speed, the images resolution were decreased to 128 × 128 pixels
with three channels; they are not suitable for high-resolution image generation. This re-
search normalizes the image color values to [−1, 1] before feeding the image into the model.

4.2. iFACADE Model Training

This research used Tensorflow to implement the model training. We also started to
generate resolutions from 8 × 8. The models were optimized by stochastic gradient descent.
For all experiments, the learning rate was fixed at 0.002, which updates the generator once
for each discriminator update.
We implemented the proposed architecture in Tensorflow using a workstation with a
NVIDIA 2080 Ti GPU. Our model uses StyleGAN [6] with the ADAM optimizer (b1 = 0.5,
b2 = 0.999) and was trained for 11 days and 6 h. The learning rates of the generator and
discriminator were both 0.0001. The stack size was 4. We set the number of critics to 1 and
used leaky RLUs (a = 0.1) for all nonlinearities, except the last one in the generator, where
the trained model used the hyperbolic tangent. Styles are configured per image by two
normalization parameters computed per feature map, and these parameters are computed
deterministically based on a global style vector w. The input image was 256 × 256 pixels in
size. We used a one-hot vector as the conditional vector. After the conditional vector was
sent to input the image size, it was concatenated with an input image in the center of the
encoder. We used StyleGAN as the discriminator. In this study, the generator was changed
once after five updates of the discriminator. For training with a 32-bit bath size, we used
Adam optimization and 20 iteration epochs. We created test photos with a resolution of
512 × 512.
Architecture 2023, 3 264

5. Results
The edition has numerous features that differ from the target, has a slightly different
color, and can be guessed, especially in the regions where the inscriptions are sparse.
However, most of the key architectural features are in place. This leads us to believe that
we can design whole new lettering plans and create realistic looking facades from them.
This could be very useful for an architect, who can sketch a design for a building and then
quickly prototype the textures (perhaps several dozens since they are so easy to create).
What happens when you combine feature settings from two different images? Since
style injection is performed separately on each layer, this can easily be done by inserting the
w vector from building B1 into a set of layers and the w vector from building B2 into the
remaining layers. This results in some planes being configured according to the parameters
of building B1 and others according to those of building B2. This is what can be seen
in the figure above. In each row, we take the leftmost image and swap a group of its
style parameters with the image in the corresponding column. In the first three rows, we
swap the coarse style parameters from the source; in the second two rows, we swap the
medium ones; and in the last row, we imported only the fine style parameters from the
alternate image “note that these are not real images, just various artificial drawings from
the z-distribution, which are then converted to a w-vector using the mapping network” as
shown in Figure 3.

Figure 3. Example images generated from inputs containing condition information specifying (a)
one, (b) two, and (c) three domains, respectively. All images are generated with the same style noise.
Our model can generate images that include class information from an input that includes condition
information that specifies multiple classes.

We find that the style-based generator (E) significantly improves the Fréchet input
distance (FID), a metric for evaluating the quality of images created with a generative
model, over the traditional generator (B), by almost 20 percent, which corroborates the
extensive ImageNet measurements from parallel work (6, 5). Figure 2 shows an uncurated
set of new images generated by our generator from the Flickr-Faces-HQ dataset (FFHQ).
As confirmed by the FIDs, the average quality is high, and even accessories such as glasses
and hats are successfully synthesized. All FIDs in this article are computed without the
cropping trick, and we use it only for illustration in Figure 2 and the video. All images are
generated at a resolution of 1024 as illustrated in Figure 4.
Architecture 2023, 3 265

Figure 4. Generating different architecture styles from one building facade by manipulating la-
tent space.

Examples of stochastic variation are as follows: (a) Two generated images. (b) Magnifi-
cation with different realizations of the input noise. While the overall appearance is almost
identical, the individual architectural elements are placed very differently. (c) Standard
deviation of each pixel over 100 different realizations, showing clearly which parts of the
images are affected by the noise. training significantly improves localization, as evidenced
by improved FIDs in scenarios where multiple latents are mixed at test time. Figure 3
shows examples of images synthesized by mixing two latent codes at different scales. We
can see that each subset of styles controls meaningful high-level attributes of the image.

6. Discussion
It is presented that iFACADE will be useful for designers in the early design phase
to create new facades in a short time depending on existing buildings, saving time and
energy. Moreover, building owners can use iFACADE to show their preferred architectural
facade to their architects by mixing two architectural styles and creating a new building.
Therefore, it is illustrated that iFACADE can become a communication platform in the early
design stages between architects and builders.
Figure 4 shows that our model generates images from the input noise styles and the
state vectors representing each class. We can see that our model can generate any class of
images, thanks to the condition vectors. However, although the sounds and styles are fixed,
the generated facades have distorted images of food because they have few round patterns.
Figure 5 shows the images generated from a fixed style, a state vector, and randomly
sampled noise. Each image is generated by our model with different random noises. We
can see that random noise plays a role in representing differences, such as food topping.
Figure 4 shows that the images generated by our model are generated simultaneously with
state vectors representing two or more classes. We can see that our model can generate any
feature, even if there are multiple condition vectors:

targeted facade = G ( x )variant of target facade = G ( x + e) (5)

where G is the generator, and e is a vector whose components are small numbers that are
sampled randomly.
The iFACADE does not work in neighborhoods that do not follow the modular
architectural style because the generated facades have characteristics of reference facades.
It also cannot be applied to new neighborhoods where buildings do not yet exist, as it relies
Architecture 2023, 3 266

on prefabricated facades as a reference to generate a new architectural style. In addition,

iFACADE cannot control the specific characteristics of individual building elements. For
example, it cannot change the style of the window openings or the height of the porch
according to the user’s preferences. For this reason, iFACADE will control each individual
building element according to the user’s wishes in the future. To address these limitations,
this research can utilize StyleGAN 2 [23], which provides better control on the latent
space and image quality. In addition, the trained dataset could be increased with different
architecture styles to give options to the user to choose the desired style according to their
preferences. Furthermore, the user could upload a collection of images, and the model
could perform architecture style transfer to the targeted facade using [7,24]. This method
needs to be tested to find the applicability and quality of generated facade images.

Figure 5. Evaluation criteria of generated facade images using trained model.

Architecture 2023, 3 267

To measure the quality of generated facade images, quantitative measures are used to
evaluate the trained model and generate new facades. A comparison between real facade
images and generated facade images was conducted. The main architectural characteristics
were analyzed. The evaluation process depends on the following features: number of
floors, walls, windows, clarity of the facade, and materials. The real facade image had
4 to 5 floors, and the generated facade images also maintained the same range of floors.
The front wall of the real facade images used were flat, and the generated facade images
had the same features. The windows in the real facade were in the range of 3, 4 and 5
windows per floor and the generated facade also maintained the same number of windows
per floor as depicted in Figure 5. The real images used had 720 pixel clarity. However,
the generated facade lost 15 percent of its clarity due to the limited graphics card used for
training. It is arguable that using fewer images for training will give better quality images,
but it will limit the variation of facade features shown in Table 1. The materials of the
facade in the real and generated images are stone and marble with materials of off-white
colors. The number of floors remained limited. The facade wall in the generated images is
of an apartment and parallel to the front view, which follows the real image. The window
details are varied because they belong to all real images and not to a target image in the
trained data-set. The clarity of the facade is good enough for a conceptual illustration. The
material and the color of the facade vary each time the model runs to generate a new image
as illustrated in Figure 5.

Table 1. Evaluating the generated facade image architecture features.

Item Real Facade Generated Facade

number of floors 4 floors 4 floors
5 floors 5 floors
walls plain facade wall plain facade wall
windows (3, 4, 5) per floor (3, 4, 5) per floor
clarity of the facade very clear 15 percent blurry
material stone and marble variety of off white color

7. Conclusions
In this research, a machine learning tool is proposed that can mix the facade style
of two reference facade images and generate a unique facade design that can be used in
urban redensification. Experiments show that the proposed model can generate different
facade images with conditional vectors. The proposed tool could also be useful for facade
designers, as it is able to quickly convert an architect’s simple building sketch into a
prototype texture. The main contributions of this research are that (a) iFACADE can mix
facade styles to generate a new facade image with its own features, (b) the latent space of
the generated image can be used to control the style details of the architectural elements of
the output image, and (c) our proposed generator can generate images representing each
feature from the condition information defining multiple classes. In the future, iFACADE
could be extended to a mobile app that can host a trained model, where the user can
simply take a photo of two desired building views, and the app generates a mixed-style
architectural facade. Then, the user can project the generated facade onto the unbuilt space
using augmented reality technology. Thus, our proposed generator based on conditional
style has great potential to solve problems that are still unsolved in food images. Finally,
we hope that our proposed model will contribute to further studies on architectural design.
Moreover, iFACADE should be extended to generate 3D facade elements in addition to
2D images so that it can be directly used in the early design stages of architecture and
increase automation.
Architecture 2023, 3 268

Author Contributions: Conceptualization, A.K.A.; methodology, O.J.L.; software, A.K.A.; valida-

tion, A.K.A.; formal analysis, O.J.L.; investigation, O.J.L.; resources, O.J.L.; data curation, A.K.A.;
writing—original draft preparation, A.K.A.; writing—review and editing, A.K.A.; visualization,
A.K.A.; supervision, O.J.L.; project administration, O.J.L.; funding acquisition, O.J.L. All authors have
read and agreed to the published version of the manuscript.
Funding: This research was funded by Haenglim for Architecture and Engineering Company.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Acknowledgments: This work is supported by Haenglim Architecture and Engineering Company.
The first author would like to thank Chung Ang University and the Korean Government Scholar-
ship program.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Adamus-Matuszyńska, A.; Michnik, J.; Polok, G. A Systemic Approach to City Image Building. The Case of Katowice City.
Sustainability 2019, 11, 4470. [CrossRef]
2. Talen, E. City Rules: How Regulations Affect Urban Form; Island Press: Washington, DC, USA, 2012.
3. Touloupaki, E.; Theodosiou, T. Performance simulation integrated in parametric 3D modeling as a method for early stage
design optimization—A review. Energies 2017, 10, 637. [CrossRef]
4. García-Ordás, M.T.; Benítez-Andrades, J.A.; García-Rodríguez, I.; Benavides, C.; Alaiz-Moretón, H. Detecting Respiratory
Pathologies Using Convolutional Neural Networks and Variational Autoencoders for Unbalancing Data. Sensors 2020, 20, 1214.
[CrossRef] [PubMed]
5. Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial
networks. Commun. ACM 2020, 63, 139–144. [CrossRef]
6. Karras, T.; Laine, S.; Aittala, M.; Hellsten, J.; Lehtinen, J.; Aila, T. Analyzing and improving the image quality of stylegan. In
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, Seattle, WA, USA, 13–19 June 2020;
pp. 8110–8119.
7. Almahairi, A.; Rajeswar, S.; Sordoni, A.; Bachman, P.; Courville, A. Augmented cyclegan: Learning many-to-many mappings
from unpaired data. arXiv 2018, arXiv:1802.10151.
8. Zhu, J.Y.; Zhang, R.; Pathak, D.; Darrell, T.; Efros, A.A.; Wang, O.; Shechtman, E. Toward multimodal image-to-image translation.
In Advances in Neural Information Processing Systems; Morgan Kaufmann Publishers: Burlington, MA, USA 2017; pp. 465–476.
9. Zhang, Y.; Yin, Y.; Zimmermann, R.; Wang, G.; Varadarajan, J.; Ng, S.K. An Enhanced GAN Model for Automatic Satellite-to-Map
Image Conversion. IEEE Access 2020, 8, 176704–176716. [CrossRef]
10. Bulat, A.; Yang, J.; Tzimiropoulos, G. To learn image super-resolution, use a gan to learn how to do image degradation first.
In Proceedings of the European Conference on Computer Vision (ECCV), 2018, Munich, Germany, 8–14 September 2018;
pp. 185–200.
11. Reed, S.; Akata, Z.; Yan, X.; Logeswaran, L.; Schiele, B.; Lee, H. Generative adversarial text to image synthesis. arXiv 2016,
arXiv:1605.05396.
12. Isola, P.; Zhu, J.Y.; Zhou, T.; Efros, A.A. Image-to-image translation with conditional adversarial networks. In Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition, 2017, Honolulu, HI, USA, 21–26 July 2017; pp. 1125–1134.
13. Zhu, J.Y.; Park, T.; Isola, P.; Efros, A.A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In
Proceedings of the IEEE International Conference on Computer Vision, 2017, Honolulu, HI, USA, 21–26 July 2017; pp. 2223–2232.
14. Choi, Y.; Choi, M.; Kim, M.; Ha, J.W.; Kim, S.; Choo, J. Stargan: Unified generative adversarial networks for multi-domain
image-to-image translation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, Salt
Lake City, UT, USA, 18–22 June 2018; pp. 8789–8797.
15. Mao, Q.; Lee, H.Y.; Tseng, H.Y.; Ma, S.; Yang, M.H. Mode seeking generative adversarial networks for diverse image synthesis.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, Long Beach, CA, USA, 16–20 June
2019; pp. 1429–1437.
16. Abdal, R.; Qin, Y.; Wonka, P. Image2stylegan: How to embed images into the stylegan latent space? In Proceedings of the IEEE
International Conference on Computer Vision, 2019, Long Beach, CA, USA, 16–20 June 2019; pp. 4432–4441.
17. Collins, E.; Bala, R.; Price, B.; Susstrunk, S. Editing in Style: Uncovering the Local Semantics of GANs. In Proceedings of the
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, Seattle, WA, USA, 14–19 June 2020; pp. 5771–5780.
18. Horita, D.; Shimoda, W.; Yanai, K. Unseen food creation by mixing existing food images with conditional stylegan. In Proceed-
ings of the 5th International Workshop on Multimedia Assisted Dietary Management, 2019, Nice, France, 21–25 October 2019;
pp. 19–24.
Architecture 2023, 3 269

19. Han, S.; Mao, H.; Dally, W.J. Deep compression: Compressing deep neural networks with pruning, trained quantization and
huffman coding. arXiv 2015, arXiv:1510.00149.
20. Tylecek, R. The Cmp Facade Database; Technical Report, CTU–CMP–2012–24; Czech Technical University: Prague, Czech
Republic, 2012.
21. Korc, F.; Förstner, W. eTRIMS Image Database for Interpreting Images of Man-Made Scenes; Technical Report, TR-IGG-P-2009-01;
Department of Photogrammetry, University of Bonn: Bonn, Germany, 2009.
22. Braun, M.; Krebs, S.; Flohr, F.; Gavrila, D.M. The eurocity persons dataset: A novel benchmark for object detection. arXiv 2018,
arXiv:1805.07193.
23. Viazovetskyi, Y.; Ivashkin, V.; Kashin, E. Stylegan2 distillation for feed-forward image manipulation. In Computer Vision–ECCV
2020: 16th European Conference, Glasgow, UK, 23–28 August 2020, Proceedings, Part XXII 16; Springer: Berlin/Heidelberg, Germany,
2020; pp. 170–186.
24. Lin, C.T.; Huang, S.W.; Wu, Y.Y.; Lai, S.H. GAN-based day-to-night image style transfer for nighttime vehicle detection. IEEE
Trans. Intell. Transp. Syst. 2020, 22, 951–963. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.