https://github.com/weizhou-geek/SFSN
공식 코드Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
3D object super-resolution is the task of up-sampling 3D objects.
<span style="color:grey; opacity: 0.6">( Image credit: Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness
Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity
Revisiting Implicit Neural Representations in Low-Level Vision
Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
DISGAN: Wavelet-informed Discriminator Guides GAN to MRI Super-resolution with Noise Cleaning
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model
Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
Hypernetworks build Implicit Neural Representations of Sounds
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
SinSR: Diffusion-Based Image Super-Resolution in a Single Step
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
GAN Prior based Null-Space Learning for Consistent Super-Resolution
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception
Underwater Image Super-Resolution using Deep Residual Multipliers
Blueprint Separable Residual Network for Efficient Image Super-Resolution
TextSR: Content-Aware Text Super-Resolution Guided by Recognition
Component Divide-and-Conquer for Real-World Image Super-Resolution
High-throughput, high-resolution registration-free generated adversarial network microscopy
Efficient Long-Range Attention Network for Image Super-resolution
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.