08_Image_Restoration
In Computer Vision, CNNs have become the dominant models for vision tasks since 2012. There is an increasing convergence of computer vision and NLP with much more efficient class of architectures.
Embedded Files
0) Overview
Dataset:
Metrics:
1) Papers:
Traditional image restoration
[28,72, 73, 62, 32]
CNN-based restoration
Since pioneering work SRCNN [18] (for image SR), DnCNN [90] (for image denoising) and ARCNN [17] (for JPEG compression artifact reduction), a flurry of CNN-based models have been proposed to improve model representation ability by using larger and deeper neural network architecture designs, such as residual block [40, 7, 88], dense block [81, 97, 98] and others [10, 42, 93, 78, 77, 79, 50, 48, 49, 92, 70, 36, 83, 30, 11, 16, 96, 64, 38, 26, 41, 25].
DBPN [31],
RRDB [81]
Attention-based restoration
Some of them have exploited the attention mechanism inside the CNN framework, such as channel attention [95, 15, 63], non-local attention [52, 61], and adaptive patch aggregation [100].
RCAN [95]
SAN [15]
HAN [63]
NLSA [61]
IGNN [100]
Light-weight
CARN [2]
FALSR-A [12]
IMDN [35]
LAPAR-A [44]
LatticeNet [57]
Real-world SR
BSRGAN [89]
ESRGAN [81]
FSSR [24]
RealSR [37]
BSRGAN [89].
JPEG Compression
ARCNN [17]
DnCNN-3 [90]
QGAC [20]
RNAN [96]
RDN [98]
DRUNet [88].
Traditional Denoising
BM3D [14]
WNNM [29]
CNN-based Denoising
DnCNN [90]
IRCNN [91]
FFDNet [92]
N3Net [65]
NLRN [52]
FOCNet [38]
RNAN [96]
MWCNN [54]
DRUNet [88]
References:
SwinIR Paper
Page updated
Google Sites
Report abuse