Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform

Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show that it is possible to recover textures faithful to semantic classes... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Introduced in the Paper:

OST300

Mentioned in the Paper:

COCO ADE20K BSD Set14 Set5
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Image Super-Resolution BSD100 - 4x upscaling SFT-GAN PSNR 25.33 # 38
SSIM 0.651 # 41
Image Super-Resolution Set14 - 4x upscaling SFT-GAN PSNR 26.13 # 49
SSIM 0.694 # 47
Image Super-Resolution Set5 - 4x upscaling SFT-GAN PSNR 29.82 # 43
SSIM 0.840 # 42

Methods used in the Paper


METHOD TYPE
Dropout
Regularization
Softmax
Output Functions
Max Pooling
Pooling Operations
PReLU
Activation Functions
Sigmoid Activation
Activation Functions
ReLU
Activation Functions
VGG
Convolutional Neural Networks
Residual Block
Skip Connection Blocks
Dense Connections
Feedforward Networks
Residual Connection
Skip Connections
Convolution
Convolutions
Leaky ReLU
Activation Functions
PixelShuffle
Miscellaneous Components
Batch Normalization
Normalization
VGG Loss
Loss Functions
SRGAN Residual Block
Skip Connection Blocks
SRGAN
Generative Adversarial Networks