HyperAI
HyperAI超神经
首页
算力平台
文档
资讯
论文
教程
数据集
百科
SOTA
LLM 模型天梯
GPU 天梯
顶会
开源项目
全站搜索
关于
中文
HyperAI
HyperAI超神经
Toggle sidebar
全站搜索…
⌘
K
Command Palette
Search for a command to run...
首页
SOTA
图像超分辨率
Image Super Resolution On Urban100 4X
Image Super Resolution On Urban100 4X
评估指标
PSNR
SSIM
评测结果
各个模型在此基准测试上的表现结果
Columns
模型名称
PSNR
SSIM
Paper Title
Repository
Hi-IR-L
28.72
0.8514
Hierarchical Information Flow for Generalized Efficient Image Restoration
-
DRCT-L
28.70
0.8508
DRCT: Saving Image Super-resolution away from Information Bottleneck
HMA†
28.69
0.8512
HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
HAT-L
28.60
0.8498
Activating More Pixels in Image Super-Resolution Transformer
HAT_FIR
28.43
-
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
DRCT
28.40
0.8457
DRCT: Saving Image Super-resolution away from Information Bottleneck
HAT
28.37
0.8447
Activating More Pixels in Image Super-Resolution Transformer
CPAT+
28.33
0.8425
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
-
CPAT
28.22
0.8408
Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution
-
IPG
28.13
0.8392
Image Processing GNN: Breaking Rigidity in Super-Resolution
-
SwinFIR
28.12
0.8393
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
MaIR+
27.89
0.8336
MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
MaIR
27.71
0.8305
MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
SwinIR
27.45
0.8254
SwinIR: Image Restoration Using Swin Transformer
HBPN
27.3
0.818
Hierarchical Back Projection Network for Image Super-Resolution
LTE
27.24
-
Local Texture Estimator for Implicit Representation Function
SAN
27.23
0.8169
Second-Order Attention Network for Single Image Super-Resolution
-
CSNLN
27.22
0.8168
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
DRLN+
27.14
0.8149
Densely Residual Laplacian Super-Resolution
DBPN-RES-MR64-3
27.08
0.814
Deep Back-Projection Networks for Single Image Super-resolution
0 of 64 row(s) selected.
Previous
Next