High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks

Prawit Boonmee; Jirayus Arbking; Prajaks Jitngernmadan; Pinphong Ruangraweenukit; Natthawat Boonkhirassamee; Kittipong Nitsaisook; Kawin Yosmao; Prawee Jarujit; Kritsanapon Worrasuwatthanakul; Suriyen Kongtip; Ponlawat Chopuk

doi:10.35377/saucis...1871911

High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks

Abstract

he rapid advancement of humanoid robotics has intensified the demand for “embodied AI” systems capable of translating abstract perception into precise physical manipulation. While robotic art serves as an excellent benchmark for such dexterity, existing systems often struggle to preserve high-frequency details, particularly in complex facial regions like the eyes, or rely on prohibitively expensive industrial hardware. To address these limitations, this research presents a novel algorithmic pipeline for high-fidelity robotic portrait drawing. We propose a “split-transform-merge” methodology utilizing a patch-partitioned Generative Adversarial Network (P2LDGAN). Unlike traditional global inference methods, which lose fine detail, our approach partitions input images into 256 × 256 patches, processes them independently to maximize local feature retention, and spatially reconstructs them for execution by a low-cost Dobot Magician robotic arm. Qualitative results demonstrate that this patch-based strategy significantly outperforms current state-of-the-art competitors in rendering smooth arcs and fine facial features. By successfully bridging modern generative AI with precise physical execution, this work provides a robust, low-cost solution for automated artistic creation and fine-motor robotic control.

Keywords

References

Founders Network, “Figure AI Raises $675M at $2.6B Valuation,” 2024. Available at https://foundersnetwork.com/
Business Wire, “Figure AI Series B Funding Announcement,” 2025. Available at https://www.businesswire.com/
Goldman Sachs Research, “Humanoid Robots: The AI Accelerant,” Goldman Sachs Equity Research, Feb. 2024. [Online].
A. Brohan et al., “RT-2: Vision-Language-Action Models Transfer Knowledge to Robotics,” arXiv preprint arXiv:2307.15818, 2023.
Shenzhen Yuejiang Technology Co., Ltd., “Dobot Magician User Guide v1.2.0,” 2023. [Online]. Available: https://www.dobot-robots.com/
P. S. Tsai, T. F. Wu, J. Y. Chen, and F. H. Lee, “Drawing system with Dobot Magician manipulator based on image processing,” Machines, vol. 9, no. 12, p. 302, 2021.
A. T. Hoang, J. Csempesz, T. Cserteg, and Z. J. Viharos, “Piktor-O-Bot: Integrated image processing algorithms for portrait drawing robot applications,” Measurement: Sensors, Art. no. 101592, 2025.
P. Tresset and F. F. Leymarie, “Portrait drawing by Paul the robot,” Computers & Graphics, vol. 37, no. 5, pp. 348–363, 2013.

E. Guizzo and E. Ackerman, “The Humanoid Robot Is Finally Here,” IEEE Spectrum, vol. 60, no. 1, pp. 26–32, Jan. 2023.
Y. Wang et al., “A Survey on Robotic Pen-Based Drawing and Writing,” IEEE Access, vol. 10, pp. 34501–34520, 2022.
J. M. Gülzow, P. Paetzold, and O. Deussen, “Recent developments regarding painting robots for research in automatic painting, artificial creativity, and machine learning,” Appl. Sci., vol. 10, p. 3396, 2020.
L. Scalera, S. Seriani, A. Gasparetto, and P. Gallina, “Non-photorealistic rendering techniques for artistic robotic painting,” Robotics, vol. 8, p. 10, 2019.
Y. Sun and Y. Xu, “A calligraphy robot—Callibot: Design, analysis and applications,” in Proc. IEEE Int. Conf. on Robotics and Biomimetics (ROBIO), 2013, pp. 85–190.
Q. Luo and J. Wu, “A generalized robotic handwriting learning system based on dynamic movement primitives (DMPs),” arXiv preprint arXiv:2012.03399, 2020.
H. Li et al., “Design and Application of AI-based Brush Calligraphy and Painting Robot,” in Proc. 2024 Int. Conf. on Artificial Life and Robotics (ICAROB), 2024.
S. Calinon, J. Epiney, and A. Billard, “A humanoid robot drawing human portraits,” in Proc. 5th IEEE-RAS Int. Conf. on Humanoid Robots, 2005, pp. 161–166.
C. Y. Lin, L. W. Chuang, and T. T. Mac, “Human portrait generation system for robot arm drawing,” in Proc. 2009 IEEE/ASME Int. Conf. on Advanced Intelligent Mechatronics, 2009, pp. 1757–1762.
G. Jean-Pierre and Z. SaId, “The artist robot: A robot drawing like a human artist,” in Proc. 2012 IEEE Int. Conf. on Industrial Technology, 2012, pp. 486–491.
X. Chen, “Anime2Sketch: A high-quality photo-to-sketch translation tool,” GitHub repository, 2021.
C. Chan, F. Durand, and P. Isola, “Learning to generate line drawings that convey geometry and semantics,” in Proc. IEEE/CVF CVPR, 2022, pp. 7915–7925.
S. Jain, P. Gupta, V. Kumar, and K. Sharma, “A force-controlled portrait drawing robot,” in Proc. IEEE Int. Conf. on Industrial Technology (ICIT), 2015, pp. 3160–3165.
P. O’Dowd, “A Robot That Draws and Shades with Tactile Force Feedback Sensed Through a Pencil,” Proc. EVA London 2019, 2019.
T. Wang et al., “RoboCoDraw: Robotic Avatar Drawing with GAN-Based Style Transfer and Time-Efficient Path Optimization,” in Proc. AAAI Conf. on Artificial Intelligence, 2020.
S. Nasrat et al., “Artistic Robotic Arm: Drawing Portraits on Physical Canvas under 80 Seconds,” Sensors, vol. 23, no. 12, 2023.
M. Adamik et al., “Fast robotic pencil drawing based on image evolution by means of genetic algorithm,” Robotics and Autonomous Systems, vol. 148, 2022.
P. Schaldenbrand, J. McCann, and J. Oh, “Frida: A collaborative robot painter with a differentiable, real2sim2real planning environment,” arXiv preprint arXiv:2210.00664, 2022.
J. Csempesz et al., “Programming and control challenges of the portrait drawing Piktor-o-bot,” presented at IMEKO, 2024.
C. Y. Fang and X. F. Han, “Joint geometric-semantic driven character line drawing generation,” in Proc. 2023 ACM Int. Conf. on Multimedia Retrieval (ICMR), 2023, pp. 226–233.
Raspberry Pi Ltd, “Raspberry Pi 4 Model B Product Brief,” 2019. [Online].
American Century Investments, “The Rise of Humanoid Robots: Market Projections,” 2024.
Trustnet, “Embodied AI: The Next Frontier,” 2024.
IPO CLUB, “Humanoids Report,” Nov. 2025.
Humanoid Guide, “State of Humanoid Robotics 2025,” 2025.
I. Otoniel et al., “Interactive system for painting artworks by regions using a robot,” Robot. Auton. Syst., vol. 121, 2019.
R. L. Avanzato, “Development of a MATLAB/ROS Interface to a Low-cost Robot Arm,” ASEE Virtual Annual Conference, 2020.
RobotDK, “Lights out Robot Painting.” Available at https://robodk.com/
Foto Master, “Draw Me Bot: The AI-Based Drawing Robot Photo Booth,” 2024.
Shenzhen Dobot Robotics Co., Ltd., “Dobot Magician Specifications,” 2017.

Details

Primary Language

English

Subjects

Applied Computing (Other), Artificial Intelligence (Other), Control Engineering, Mechatronics and Robotics (Other)

Journal Section

Research Article

Authors

Prawit Boonmee
0009-0005-8278-6389
Thailand

Jirayus Arbking
0009-0005-7403-8938
Thailand

Prajaks Jitngernmadan
0009-0009-6138-4021
Thailand

Pinphong Ruangraweenukit
0009-0008-1055-4628
Thailand

Natthawat Boonkhirassamee
0009-0007-8226-8711
Thailand

Kittipong Nitsaisook
0009-0003-6906-0108
Thailand

Kawin Yosmao
0009-0003-8960-7449
Thailand

Prawee Jarujit
0009-0000-3349-5570
Thailand

Kritsanapon Worrasuwatthanakul
0009-0003-3251-1307
Thailand

Suriyen Kongtip
0009-0009-0359-0249
Thailand

Ponlawat Chopuk ^*
0000-0002-7284-2675
Thailand

Early Pub Date

June 23, 2026

Publication Date

June 30, 2026

Submission Date

January 26, 2026

Acceptance Date

April 30, 2026

Published in Issue

Year 2026 Volume: 9 Number: 3

DOI

https://doi.org/10.35377/saucis...1871911

IZ

https://izlik.org/JA72FP97LD

Cite

RIS / Bibtex

APA

Boonmee, P., Arbking, J., Jitngernmadan, P., Ruangraweenukit, P., Boonkhirassamee, N., Nitsaisook, K., Yosmao, K., Jarujit, P., Worrasuwatthanakul, K., Kongtip, S., & Chopuk, P. (2026). High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks. Sakarya University Journal of Computer and Information Sciences, 9(3), 775-789. https://doi.org/10.35377/saucis...1871911

AMA

1.Boonmee P, Arbking J, Jitngernmadan P, et al. High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks. SAUCIS. 2026;9(3):775-789. doi:10.35377/saucis.1871911

Chicago

Boonmee, Prawit, Jirayus Arbking, Prajaks Jitngernmadan, et al. 2026. “High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks”. Sakarya University Journal of Computer and Information Sciences 9 (3): 775-89. https://doi.org/10.35377/saucis. 1871911.

EndNote

Boonmee P, Arbking J, Jitngernmadan P, Ruangraweenukit P, Boonkhirassamee N, Nitsaisook K, Yosmao K, Jarujit P, Worrasuwatthanakul K, Kongtip S, Chopuk P (June 1, 2026) High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks. Sakarya University Journal of Computer and Information Sciences 9 3 775–789.

IEEE

[1]P. Boonmee et al., “High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks”, SAUCIS, vol. 9, no. 3, pp. 775–789, June 2026, doi: 10.35377/saucis...1871911.

ISNAD

Boonmee, Prawit - Arbking, Jirayus - Jitngernmadan, Prajaks - Ruangraweenukit, Pinphong - Boonkhirassamee, Natthawat - Nitsaisook, Kittipong - Yosmao, Kawin et al. “High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks”. Sakarya University Journal of Computer and Information Sciences 9/3 (June 1, 2026): 775-789. https://doi.org/10.35377/saucis. 1871911.

JAMA

1.Boonmee P, Arbking J, Jitngernmadan P, Ruangraweenukit P, Boonkhirassamee N, Nitsaisook K, Yosmao K, Jarujit P, Worrasuwatthanakul K, Kongtip S, Chopuk P. High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks. SAUCIS. 2026;9:775–789.

MLA

Boonmee, Prawit, et al. “High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 3, June 2026, pp. 775-89, doi:10.35377/saucis. 1871911.

Vancouver

1.Prawit Boonmee, Jirayus Arbking, Prajaks Jitngernmadan, Pinphong Ruangraweenukit, Natthawat Boonkhirassamee, Kittipong Nitsaisook, Kawin Yosmao, Prawee Jarujit, Kritsanapon Worrasuwatthanakul, Suriyen Kongtip, Ponlawat Chopuk. High-Fidelity Robotic Portraiture via Patch-Based Generative Adversarial Networks. SAUCIS. 2026 Jun. 1;9(3):775-89. doi:10.35377/saucis. 1871911