Mohamed Abbas Hedjazi
Mohamed Abbas Hedjazi has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Yakup Genc
Gebze Technical University
3 shared publications - Adel Hafiane
University d’Orléans
1 shared publication - Antoine Letienne
DASIA
1 shared publication - Oussama Hadjerci
DASIA
1 shared publication - Yakup Genc
Gebze Technical University 41400 Kocaeli Turkey
1 shared publication
Latest Publications
- 20 January 2026
- Published by Springer Nature
- p. 297-309
Self-supervised Structured Object Representation Learning
- 20 January 2026
- Published by Springer Nature
- p. 297-309
Self-supervised Structured Object Representation Learning
- 1 April 2021
- Published by Elsevier in Knowledge-Based Systems
- Vol. 217
Efficient texture-aware multi-GAN for image inpainting
- 1 April 2021
- Published by Elsevier in Knowledge-Based Systems
- Vol. 217
Efficient texture-aware multi-GAN for image inpainting
- Open Access
Efficient texture-aware multi-GAN for image inpainting
Recent GAN-based (Generative adversarial networks) inpainting methods show remarkable improvements and generate plausible images using multi-stage networks or Contextual Attention Modules (CAM). However, these techniques increase the model complexity limiting their application in low-resource environments. Furthermore, they fail in generating high-resolution images with realistic texture details due to the GAN stability problem. Motivated by these observations, we propose a multi-GAN architecture improving both the performance and rendering efficiency. Our training schema optimizes the parameters of four progressive efficient generators and discriminators in an end-to-end manner. Filling in low-resolution images is less challenging for GANs due to the small dimensional space. Meanwhile, it guides higher resolution generators to learn the global structure consistency of the image. To constrain the inpainting task and ensure fine-grained textures, we adopt an LBP-based loss function to minimize the difference between the generated and the ground truth textures. We conduct our experiments on Places2 and CelebHQ datasets. Qualitative and quantitative results show that the proposed method not only performs favorably against state-of-the-art algorithms but also speeds up the inference time.
Open AccessEfficient texture-aware multi-GAN for image inpainting
Recent GAN-based (Generative adversarial networks) inpainting methods show remarkable improvements and generate plausible images using multi-stage networks or Contextual Attention Modules (CAM). However, these techniques increase the model complexity limiting their application in low-resource environments. Furthermore, they fail in generating high-resolution images with realistic texture details due to the GAN stability problem. Motivated by these observations, we propose a multi-GAN architecture improving both the performance and rendering efficiency. Our training schema optimizes the parameters of four progressive efficient generators and discriminators in an end-to-end manner. Filling in low-resolution images is less challenging for GANs due to the small dimensional space. Meanwhile, it guides higher resolution generators to learn the global structure consistency of the image. To constrain the inpainting task and ensure fine-grained textures, we adopt an LBP-based loss function to minimize the difference between the generated and the ground truth textures. We conduct our experiments on Places2 and CelebHQ datasets. Qualitative and quantitative results show that the proposed method not only performs favorably against state-of-the-art algorithms but also speeds up the inference time.
- 14 January 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 93, 116148
Image inpainting using scene constraints
- 14 January 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 93, 116148
Image inpainting using scene constraints
- Open Access
Learning to Inpaint by Progressively Growing the Mask Regions
Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images. However, they still have difficulties to generate the correct structures and colors as the masked region grows large. This drawback is due to the training stability issue of the generative models. This work introduces a new curriculum-style training approach in the context of image inpainting. The proposed method increases the masked region size progressively in training time, during test time the user gives variable size and multiple holes at arbitrary locations. Incorporating such an approach in GANs may stabilize the training and provides better color consistencies and captures object continuities. We validate our approach on the MSCOCO and CelebA datasets. We report qualitative and quantitative comparisons of our training approach in different models.
Open AccessLearning to Inpaint by Progressively Growing the Mask Regions
Image inpainting is one of the most challenging tasks in computer vision. Recently, generative-based image inpainting methods have been shown to produce visually plausible images. However, they still have difficulties to generate the correct structures and colors as the masked region grows large. This drawback is due to the training stability issue of the generative models. This work introduces a new curriculum-style training approach in the context of image inpainting. The proposed method increases the masked region size progressively in training time, during test time the user gives variable size and multiple holes at arbitrary locations. Incorporating such an approach in GANs may stabilize the training and provides better color consistencies and captures object continuities. We validate our approach on the MSCOCO and CelebA datasets. We report qualitative and quantitative comparisons of our training approach in different models.