U-Paint: Image Inpainting and Object Detection via Partial Convolutions

Rahul Singh; Martin Bruder; Akshay Kumar; Rohan Joshi

doi:doi:10.11648/j.ijimse.20251001.12

Research Article |

| Peer-Reviewed

U-Paint: Image Inpainting and Object Detection via Partial Convolutions

Rahul Singh^*, Martin Bruder, Akshay Kumar, Rohan Joshi

Published in International Journal of Industrial and Manufacturing Systems Engineering (Volume 10, Issue 1)

Received: 18 February 2025 Accepted: 6 March 2025 Published: 13 September 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.

Published in	International Journal of Industrial and Manufacturing Systems Engineering (Volume 10, Issue 1)
DOI	10.11648/j.ijimse.20251001.12
Page(s)	9-19
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Image Inpainting, Object Detection, Partial Convolution, U-Net, Mask R-CNN, Semantic Image Segmentation

References

[1]	Liu, G., Tao, T. W. A., Catanzaro, B. (2018) Image Inpainting for Irregular Holes Using Partial Convolutions. Computer Vision and Pattern Recognition (cs. CV).
[2]	Sun, J., Yuan, L., Jia, J., Shum, H. (2005) Image Completion with Structure Propagation. ACM Transactions on Graphics. https://doi.org/10.1145/1186822.1073274
[3]	Pearl, J. (1988) Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann Publishers, Inc.
[4]	Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D. B. (2009) Patchmatch: A randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics-TOG.
[5]	Köhler R., Schuler C., Schölkopf B., Harmeling S. (2014) Mask-Specific Inpainting with Deep Neural Networks. Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science, vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_43
[6]	Yeh, R. A., Chen, C., Yian Lim, T., Schwing, A. G., Hasegawa-Johnson, M., & Do, M. N. (2017) Semantic image inpainting with deep generative models. 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 6882-6890. https://doi.org/10.1109/CVPR.2017.728
[7]	Ulyanov, D., Vedaldi, A., Lempitsky, V. (2017), Deep Image Prior, arXiv: 1711.10925 [cs. CV].
[8]	Ronneberger O., Fischer P., Brox T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N., Hornegger J., Wells W., Frangi A. (eds), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, vol 9351. https://doi.org/10.48550/arXiv.1505.04597
[9]	Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014) Rich feature hierarchies for accurate object detection and semantic segmentation, arXiv: 1311.2524 [cs. CV]. https://doi.org/10.48550/arXiv.1311.2524
[10]	He, K., Gkioxari, G., Dollár, P., Girshick, R. (2018) Mask R-CNN, arXiv: 1703.06870 [cs. CV].
[11]	Lin TY. et al. (2014) Microsoft COCO: Common Objects in Context. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision - ECCV 2014, vol 8693. Springer, Cham.
[12]	Zhou, B., Khosla, A., Lapedriza, A., Torralba, A., Oliva, A. Places: A 10 million Image Database for Scene Recognition, arXiv:1610.02055. https://doi.org/10.48550/arXiv.1610.02055
[13]	Liu, Z. & Luo, P. & Wang, X.& Tang, X. (2018) Deep Learning Face Attributes in the Wild. Proceedings of International Conference on Computer Vision (ICCV).
[14]	Singh, R., Bodhe, A., Kanuparthi, P., Ananthakrishnan, A. and Pitt, J. (2019) From classification to definition: The changing nature of human adjudication, IEEE Technol. Soc. Mag., vol. 38, no. 4, pp. 55-62. https://doi.org/10.1109/MTS.2019.2948441
[15]	Oktay, O., Schlemper, J., Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., Glocker, B., Rueckert, D. (2018) Attention U-Net: Learning Where to Look for the Pancreas, arXiv: 1804.03999 [cs. CV]. https://doi.org/10.48550/arXiv.1804.03999
[16]	Singh, R., Bruder, M., Joshi, R., Kumar, A. An Adversarial Approach to Image Inpainting. GitHub repository, https://github.com/RealBrionac/PartialConv_Tensorflow
[17]	Singh, R. (2023) Cost Optimization of Neural Models for Inpainting, ResearchGate, press.
[18]	Bodhe, A. R., Singh, R., and Bawa, A. (2016) An Internet of Things solution for sustainable domestic water consumption, International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), Bengaluru, India, pp. 224-229.
[19]	Umapathy, A., Radhakrishnan, K., Jain, K., and Singh, R. (2020) CiteQA@CLSciSumm 2020. In Proceedings of the First Workshop on Scholarly Document Processing, Association for Computational Linguistics, pp. 297-302. https://doi.org/10.18653/v1/2020.sdp-1.34
[20]	Singh, R. (2024) AudioFacialMatrix: Dataset for Voice and Face AI, 8th CSITSS IEEE, Bengaluru, India, pp. 1-5. https://doi.org/10.1109/CSITSS64042.2024.10816934
[21]	Singh, R. (2024) The Recommender System Paradox: Autonomy in the Age of AI Recommendations, 2024 3rd International Joint Conference on Information and Communication Engineering (JCICE), pp. 139-143. https://doi.org/10.1109/JCICE61382.2024.00037
[22]	Singh, R. (2023) Related Rhythms: Recommendation System To Discover Music You May Like, arXiv: 2309.13544 [cs. IR]. https://doi.org/10.48550/arXiv.2309.13544

Cite This Article

Plain Text BibTeX RIS

APA Style

Singh, R., Bruder, M., Kumar, A., Joshi, R. (2025). U-Paint: Image Inpainting and Object Detection via Partial Convolutions. International Journal of Industrial and Manufacturing Systems Engineering, 10(1), 9-19. https://doi.org/10.11648/j.ijimse.20251001.12

Copy | Download

ACS Style

Singh, R.; Bruder, M.; Kumar, A.; Joshi, R. U-Paint: Image Inpainting and Object Detection via Partial Convolutions. Int. J. Ind. Manuf. Syst. Eng. 2025, 10(1), 9-19. doi: 10.11648/j.ijimse.20251001.12

Copy | Download

AMA Style

Singh R, Bruder M, Kumar A, Joshi R. U-Paint: Image Inpainting and Object Detection via Partial Convolutions. Int J Ind Manuf Syst Eng. 2025;10(1):9-19. doi: 10.11648/j.ijimse.20251001.12

Copy | Download

@article{10.11648/j.ijimse.20251001.12,
  author = {Rahul Singh and Martin Bruder and Akshay Kumar and Rohan Joshi},
  title = {U-Paint: Image Inpainting and Object Detection via Partial Convolutions
},
  journal = {International Journal of Industrial and Manufacturing Systems Engineering},
  volume = {10},
  number = {1},
  pages = {9-19},
  doi = {10.11648/j.ijimse.20251001.12},
  url = {https://doi.org/10.11648/j.ijimse.20251001.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijimse.20251001.12},
  abstract = {Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - U-Paint: Image Inpainting and Object Detection via Partial Convolutions

AU  - Rahul Singh
AU  - Martin Bruder
AU  - Akshay Kumar
AU  - Rohan Joshi
Y1  - 2025/09/13
PY  - 2025
N1  - https://doi.org/10.11648/j.ijimse.20251001.12
DO  - 10.11648/j.ijimse.20251001.12
T2  - International Journal of Industrial and Manufacturing Systems Engineering
JF  - International Journal of Industrial and Manufacturing Systems Engineering
JO  - International Journal of Industrial and Manufacturing Systems Engineering
SP  - 9
EP  - 19
PB  - Science Publishing Group
SN  - 2575-3142
UR  - https://doi.org/10.11648/j.ijimse.20251001.12
AB  - Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.

VL  - 10
IS  - 1
ER  -

Copy | Download

Author Information

Rahul Singh

Language Technology Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania

Contact Email
Martin Bruder

Language Technology Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania

Contact Email
Akshay Kumar

Language Technology Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania

Contact Email
Rohan Joshi

Language Technology Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania

Contact Email

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Singh, R., Bruder, M., Kumar, A., Joshi, R. (2025). U-Paint: Image Inpainting and Object Detection via Partial Convolutions. International Journal of Industrial and Manufacturing Systems Engineering, 10(1), 9-19. https://doi.org/10.11648/j.ijimse.20251001.12

Copy | Download

ACS Style

Singh, R.; Bruder, M.; Kumar, A.; Joshi, R. U-Paint: Image Inpainting and Object Detection via Partial Convolutions. Int. J. Ind. Manuf. Syst. Eng. 2025, 10(1), 9-19. doi: 10.11648/j.ijimse.20251001.12

Copy | Download

AMA Style

Singh R, Bruder M, Kumar A, Joshi R. U-Paint: Image Inpainting and Object Detection via Partial Convolutions. Int J Ind Manuf Syst Eng. 2025;10(1):9-19. doi: 10.11648/j.ijimse.20251001.12

Copy | Download

@article{10.11648/j.ijimse.20251001.12,
  author = {Rahul Singh and Martin Bruder and Akshay Kumar and Rohan Joshi},
  title = {U-Paint: Image Inpainting and Object Detection via Partial Convolutions
},
  journal = {International Journal of Industrial and Manufacturing Systems Engineering},
  volume = {10},
  number = {1},
  pages = {9-19},
  doi = {10.11648/j.ijimse.20251001.12},
  url = {https://doi.org/10.11648/j.ijimse.20251001.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijimse.20251001.12},
  abstract = {Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.
},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - U-Paint: Image Inpainting and Object Detection via Partial Convolutions

AU  - Rahul Singh
AU  - Martin Bruder
AU  - Akshay Kumar
AU  - Rohan Joshi
Y1  - 2025/09/13
PY  - 2025
N1  - https://doi.org/10.11648/j.ijimse.20251001.12
DO  - 10.11648/j.ijimse.20251001.12
T2  - International Journal of Industrial and Manufacturing Systems Engineering
JF  - International Journal of Industrial and Manufacturing Systems Engineering
JO  - International Journal of Industrial and Manufacturing Systems Engineering
SP  - 9
EP  - 19
PB  - Science Publishing Group
SN  - 2575-3142
UR  - https://doi.org/10.11648/j.ijimse.20251001.12
AB  - Image inpainting and object detection are two well-established research areas with significant real-world applications in computer vision, digital forensics, media editing, and augmented reality. Image inpainting is a technique used to restore missing, distorted, or removed sections of an image, often to recreate its original appearance. It can also be applied to remove objects from an image while reconstructing the background in a visually coherent manner. Traditional inpainting methods relied on manual editing or simple interpolation techniques, whereas modern deep learning-based approaches utilize convolutional neural networks (CNNs) and generative adversarial networks (GANs) to achieve realistic results. Object detection, on the other hand, involves identifying and localizing specific objects, such as people, buildings, or vehicles, within digital images and videos. This paper presents a system that integrates object detection with image inpainting to automate object removal and image restoration. By detecting an object and applying advanced inpainting techniques, the system seamlessly reconstructs the image without noticeable artifacts. The proposed approach has broad applications in image editing, surveillance, content moderation, and privacy protection, providing an effective and automated solution for object removal and background restoration.

VL  - 10
IS  - 1
ER  -

Copy | Download