Papers with Code 아카이브
Super-Resolution
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 1
- 보존된 평가 기록
- 1
Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.
<span style="color:grey; opacity: 0.6">( Credit: MemNet )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dhrim/cau_2021
https://github.com/dhrim/t-academy_2021
https://github.com/dhruvgrover1251/Playing_with_GANs
https://github.com/diff7/DARTS-devices
https://github.com/dimawork1981/super_resolution_bot
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/dineshzende/awesome-deep-learning-resources
https://github.com/diningeachox/Image-Super-Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/divamgupta/stable-diffusion-tensorflow
High-Resolution Image Synthesis with Latent Diffusion Models
https://github.com/divyam96/EESRGAN
https://github.com/djsinghnegi/SRINImageEnhancemrntGAN
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/dkoleber/multi_style_transfer
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/CSD
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
https://github.com/dmcv-ecnu/MindSpore_ModelZoo/tree/main/SinGanMindspore
SinGAN: Learning a Generative Model from a Single Natural Image
https://github.com/dminzi98/super-resolution-for-MRIs
Enhanced Deep Residual Networks for Single Image Super-Resolution
https://github.com/dniku/perceptual-gradient-networks
https://github.com/dnwjddl/Inpainting
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/doantienthongbku/ESRGAN
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
https://github.com/doantienthongbku/SRGAN-Pytorch
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/dokyeongK/Pytorch_SRCNN
https://github.com/dokyeongK/Single-Image-Super-Resolution-Reimplemenation
https://github.com/donand/GAN_pytorch
https://github.com/dongheehand/RCAN-tf
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
https://github.com/dongyan007/Pretrained-IPT-main-master
https://github.com/dreamgonfly/GAN-tutorial
https://github.com/drhdr-user/drhdr
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
https://github.com/dslisleedh/NAFNet-flax
https://github.com/dslisleedh/NCNet-flax
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
https://github.com/dxyang/styletransfer
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
https://github.com/dzld00/adaptive-feature-interpolation-for-low-shot-image-generation
Manifold Matching via Deep Metric Learning for Generative Modeling
https://github.com/ecnusr/etds
https://github.com/edzq/WaveletSRGAN
Image Super-Resolution Using a Wavelet-based Generative Adversarial Network
https://github.com/eltechno/pulse
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
https://github.com/epochlab/xres
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://github.com/ericoldgren/kex---ct-reconstruction
https://github.com/eriklindernoren/Keras-GAN
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.