Edge-Aware Image Super-Resolution Using a Generative Adversarial Network

Das, Bishshoy; Roy, Sumantra Dutta

doi:10.1007/s42979-022-01561-8

Cited by 3 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such method is the use of space-time interest spots, which have shown strong resistance to picture fluctuations and have been employed in various investigations. Several methods have been suggested for descriptor calculation, including histograms of optical flow [8] and HOG features [9,10], and for keypoint identification, including [6,7] and [9,10]. Many methods have recently taken advantage of deep learning capabilities to recognize activities.…”

Section: Action Recognition From Rgb Imagesmentioning

confidence: 99%

Human Activity Recognition Through Images Using a Deep Learning Approach

SaiRamesh,

Dhanalakshmi,

2024

Preprint

View full text Add to dashboard Cite

Human activity recognition (HAR) identifies and classifies patterns in image data that represent human activity. It is an essential problem in many fields, such as health care, where it can monitor patients and improve their care. It is also of commercial importance, as people increasingly use smart devices and want to customize services and products based on their features. It has many applications in fields such as artificial intelligence, human-computer interaction, and health care. In particular, it helps develop context-aware systems in pervasive computing. It is used in rehabilitation for functional diagnosis and evaluating health outcomes. Recognizing human activities is also critical in measuring participation, quality of life, and lifestyle. The proposed model aims at automatic recognition of human actions in images. Also, it will recognize an automatic understanding of what actions occur in an image performed by a human. This process is complex due to the many challenges, including variations in human shape and motion, occlusion, cluttered backgrounds, illumination conditions, and viewpoint variations. Deep learning models are particularly well suited to solving HAR tasks, as they can learn complex patterns from large amounts of data. However, training deep learning models can be time-consuming and require a lot of computational resources, making it challenging to develop effective HAR systems. This paper proposes a solution to this problem by using three different deep learning models based on transfer learning, which allows the user to train the model quickly and efficiently. Transfer learning is a method in which a model trained on one task is fine-tuned for a different but related task. These approaches help to reduce the time and computational resources needed to train the model. The proposed model uses convolutional neural networks (CNN) layers inside pre-trained models to extract and classify features from image data into different human activities. Additionally, the suggested model employs transfer learning to quickly fine-tune the CNN's weights for the particular job of HAR by initializing them with those learned from a pre-trained model. By using this method, the model's performance may be enhanced while using less processing power and training time. The process of training and combining numerous models into a single, more accurate prediction is known as ensemble learning. This study used an ensemble technique to combine the predictions of four models: VGG16, RESNET50, EfficientNetB6, and a non-trained CNN model. By using diverse models, we could capture various patterns and features in the time series data, improving our system's overall accuracy. It combines the predictions of these four models with a fusion method called averaging. It involves taking the average predicted scores for each activity across all four models and selecting the activity with the highest average score as the final prediction. This approach can reduce the effects of overfitting, as it allows the models to compensate for each other's errors. As a result, this model's accuracy is further enhanced due to ensemble learning and score-level fusion. Overall, our proposed system represents a more robust and practical approach to human activity recognition than existing models.

show abstract

Section: Action Recognition From Rgb Imagesmentioning

confidence: 99%

Human Activity Recognition Through Images Using a Deep Learning Approach

SaiRamesh,

Dhanalakshmi,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…They also introduce a new loss function based on Mean Opinion Score (MOS) to evaluate the quality of the generated images. EaSRGAN [3] improves upon SRGAN by incorporating multi-stage training for the generator and discriminator, with a focus on edge and flat region enhancement. This approach pays attention to the perceptual edge information, resulting in fewer artifacts and higher image quality.…”

Section: Introductionmentioning

confidence: 99%

ConvSRGAN: super-resolution inpainting of traditional Chinese paintings

Hu,

Peng,

et al. 2024

Herit Sci

View full text Add to dashboard Cite

Existing image super-resolution methods have made remarkable advancements in enhancing the visual quality of real-world images. However, when it comes to restoring Chinese paintings, these methods encounter unique challenges. This is primarily due to the difficulty in preserving intricate non-realistic details and capturing comple semantic information with high dimensionality. Moreover, the preservation of the original artwork’s distinct style and subtle artistic nuances further amplifies this complexity. To address these challenges and effectively restore traditional Chinese paintings, we propose a Convolutional Super-Resolution Generative Adversarial Network for Chinese landscape painting super-resolution, termed ConvSRGAN. We employ Enhanced Adaptive Residual Module to delve deeply into multi-scale feature extraction in images, incorporating an Enhanced High-Frequency Retention Module that leverages an Adaptive Deep Convolution Block to capture fine-grained high-frequency details across multiple levels. By combining the Multi-Scale Structural Similarity loss with conventional losses, our ConvSRGAN ensures that the model produces outputs with improved fidelity to the original image’s texture and structure. Experimental validation demonstrates significant qualitative and quantitative results when processing traditional paintings and murals datasets, particularly excelling in high-definition reconstruction tasks for landscape paintings. The reconstruction effect showcases enhanced visual fidelity and liveliness, thus affirming the effectiveness and applicability of our approach in cultural heritage preservation and restoration.

show abstract

ConvSRGAN: Super-Resolution Inpainting of Traditional Chinese Paintings

Hu,

Xie,

Xue

et al. 2024

Preprint

View full text Add to dashboard Cite

Existing image super-resolution methods have made remarkable advancements in enhancing the visual quality of real-world images. However, when it comes to restoring Chinese paintings, these methods encounter unique challenges. This is primarily due to the difficulty in preserving intricate non-realistic details and capturing complex semantic information with high dimensionality. Moreover, the preservation of the original artwork’s distinct style and subtle artistic nuances fur- ther amplifies this complexity. To address these challenges and effectively restore traditional Chinese paintings, we propose a Convolutional Super-Resolution Gen- erative Adversarial Network (ConvSRGAN) framework specifically designed for Chinese landscape painting super-resolution. Our ConvSRGAN employs several Enhanced Adaptive Residual Modules (EARM) to delve deeply into multi- scale feature extraction in images, incorporating an Enhanced High-Frequency Retention Module (EHRM) that leverages an Adaptive Deep Convolution Block (ADCB) to capture fine-grained high-frequency details across multiple levels. By combining the Multi-Scale Structural Similarity (MS-SSIM) loss with con- ventional losses, our ConvSRGAN ensures that the model produces outputs with improved fidelity to the original image’s texture and structure. Experimen- tal validation demonstrates significant qualitative and quantitative results when 1 processing traditional paintings and murals datasets, particularly excelling in high-definition reconstruction tasks for landscape paintings. The reconstruction effect showcases enhanced visual fidelity and liveliness, thus affirming the effec- tiveness and applicability of our approach in cultural heritage preservation and restoration.

show abstract

Edge-Aware Image Super-Resolution Using a Generative Adversarial Network

Cited by 3 publications

References 26 publications

Human Activity Recognition Through Images Using a Deep Learning Approach

Human Activity Recognition Through Images Using a Deep Learning Approach

ConvSRGAN: super-resolution inpainting of traditional Chinese paintings

ConvSRGAN: Super-Resolution Inpainting of Traditional Chinese Paintings

Contact Info

Product

Resources

About