https://github.com/testestzxcv/DeblurGAN
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Blind Image Deblurring is a classical problem in image processing and computer vision, which aims to recover a latent image from a blurred input.
Source: Learning a Discriminative Prior for Blind Image Deblurring
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
Back-Projection based Fidelity Term for Ill-Posed Linear Inverse Problems
AutoSTR: Efficient Backbone Search for Scene Text Recognition
Restormer: Efficient Transformer for High-Resolution Image Restoration
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration
Recurrent Video Restoration Transformer with Guided Deformable Attention
Gated Fusion Network for Joint Image Deblurring and Super-Resolution
Diffusion Posterior Sampling for General Noisy Inverse Problems
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.