paper-with-me

홈 › Papers

A comparative analysis of SRGAN models

2023-07-18 · Fatemeh Rezapoor Nikroo, Ajinkya Deshmukh, Anantha Sharma, Adrian Tam, Kaarthik Kumar, Cleo Norris, Aditya Dangi

In this study, we evaluate the performance of multiple state-of-the-art SRGAN (Super Resolution Generative Adversarial Network) models, ESRGAN, Real-ESRGAN and EDSR, on a benchmark dataset of real-world images which undergo degradation using a pipeline. Our results show that some models seem to significantly increase the resolution of the input images while preserving their visual quality, this is assessed using Tesseract OCR engine. We observe that EDSR-BASE model from huggingface outperforms the remaining candidate models in terms of both quantitative metrics and subjective visual quality assessments with least compute overhead. Specifically, EDSR generates images with higher peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values and are seen to return high quality OCR results with Tesseract OCR engine. These findings suggest that EDSR is a robust and effective approach for single-image super-resolution and may be particularly well-suited for applications where high-quality visual fidelity is critical and optimized compute.

📄 PDF Abstract BibTeX arXiv:2307.09456

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkImage Super-ResolutionOptical Character Recognition (OCR)SSIMSuper-Resolution

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Ethereum Customer Service Number +1-833-534-1729 설명 없음
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Texture and Noise Dual Adaptation for Infrared Image Super-Resolution

2023-11-15 · Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Yafei Dong 외

Recent efforts have explored leveraging visible light images to enrich texture details in infrared (IR) super-resolution. However, this direct adaptation approach often becomes a double-edged sword, as it improves textur…

Domain AdaptationImage Super-ResolutionInfrared image super-resolutionSuper-Resolution

Using Super-Resolution Imaging for Recognition of Low-Resolution Blurred License Plates: A Comparative Study of Real-ESRGAN, A-ESRGAN, and StarSRGAN

2024-03-20 · Ching-Hsiang Wang

With the robust development of technology, license plate recognition technology can now be properly applied in various scenarios, such as road monitoring, tracking of stolen vehicles, detection at parking lot entrances a…

License Plate RecognitionSuper-Resolution

Efficient Medicinal Image Transmission and Resolution Enhancement via GAN

2024-11-19 · Rishabh Kumar Sharma, Mukund Sharma, Pushkar Sharma, Jeetashree Aparjeeta

While X-ray imaging is indispensable in medical diagnostics, it inherently carries with it those noises and limitations on resolution that mask the details necessary for diagnosis. B/W X-ray images require a careful bala…

DiagnosticSuper-Resolution

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

2018-09-01 · Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu 외

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied…

Face HallucinationGenerative Adversarial NetworkImage Super-ResolutionSuper-Resolution+1

PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations

2025-05-10 · Md Rakibul Hasan, Pouria Behnoudfar, Dan MacKinlay, Thomas Poulet

Machine Learning, particularly Generative Adversarial Networks (GANs), has revolutionised Super Resolution (SR). However, generated images often lack physical meaningfulness, which is essential for scientific application…

Generative Adversarial NetworkSuper-Resolution