nafnet

使用NAFNet进行图像去模糊

colab list for image (upscale, enhance, generation)

Restore image using NAFNet model with streamlit dashboard

Fast and practical image deraining with PyTorch.

colab list for video

A framework to develop Deep learning based Image restoration models using Tensorflow

License Plate Recognition using YOLOv8 + EasyOCR + NAFNet

Deep learning-based image restoration pipeline with DnCNN, NAFNet, and legacy joint models. Includes PSNR/SSIM/LPIPS evaluation and visual comparisons.

A Comparative Study of CNN-Based Image Restoration Methods

AI-based restoration of noisy, low-resolution semiconductor SEM images

損傷した古典籍くずし字画像のマスクガイド付き二段階修復フレームワーク — UNet++による文字領域推定 + 5種の復元モデル比較/ Mask-guided two-stage framework for restoring damaged Kuzushiji documents

PyTorch reproduction of NAFNet (ECCV 2022 'Simple Baselines for Image Restoration') on GoPro deblurring and SIDD denoising

Clinical Chest X-Ray Denoising & Radiograph Restoration Engine using NAFNet (ECCV 2022), FastAPI, and React.

PyTorch reproduction of NAFNet (ECCV 2022 'Simple Baselines for Image Restoration') on GoPro deblurring and SIDD denoising

NAFNet-SR (2.39M parameters) deep learning solution for semiconductor wafer image restoration and 2x super-resolution. Achieves 28.98 dB PSNR / 0.776 SSIM (+5.97 dB gain) with real-time GPU inference. KLA Hackathon 2026.

End-to-end deep-learning framework that super-resolves and colorizes monochrome infrared (IR) satellite imagery into realistic, semantically-faithful RGB - no hallucinations - to boost object interpretation. Bharatiya Antariksh Hackathon 2026 · Problem Statement 10.

developed an adaptive X-ray denoising framework that intelligently routes each pixel through either a fast direct-mapping path (Enhanced NAFNet) or a high-fidelity diffusion path, ensuring high-quality, structurally accurate, and computationally efficient enhancement of noisy radiographs.

Research-grade PyTorch framework for restoring degraded low-dose SEM images using NAFNet, with emphasis on noise reduction, structural fidelity, and semiconductor defect inspection.

Deep learning restoration for degraded scanned documents, trained on synthetic degradation and evaluated on both image quality and OCR readability

AI models (ONNX) for FlipsiColor – NAFNet, Restormer, RealESRGAN, RealHATGAN, CodeFormer, AiLUT, EfficientNet — KI-Modelle für FlipsiColor