HyperAI
Home
News
Latest Papers
Tutorials
Datasets
Wiki
SOTA
LLM Models
GPU Leaderboard
Events
Search
About
English
HyperAI
Toggle sidebar
Search the site…
⌘
K
Home
SOTA
Deblurring
Deblurring On Realblur R Trained On Gopro
Deblurring On Realblur R Trained On Gopro
Metrics
PSNR (sRGB)
SSIM (sRGB)
Results
Performance results of various models on this benchmark
Columns
Model Name
PSNR (sRGB)
SSIM (sRGB)
Paper Title
Repository
LaKDNet
36.08
0.955
Revisiting Image Deblurring with an Efficient ConvNet
Pan et al
34.01
0.916
Blind Image Deblurring Using Dark Channel Prior
-
Xu et al
-
0.937
Unnatural L0 Sparse Representation for Natural Image Deblurring
-
MPRNet
35.99
0.952
Multi-Stage Progressive Image Restoration
SRN
-
0.947
Scale-recurrent Network for Deep Image Deblurring
ALGNet
36.35
0.961
Learning Enriched Features via Selective State Spaces Model for Efficient Image Deblurring
AdaRevD
36.53
0.957
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
DMPHN
-
0.948
Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
Restormer
36.19
0.957
Restormer: Efficient Transformer for High-Resolution Image Restoration
DeblurDiNAT-L
36.09
0.955
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains
Zhang et al
-
0.947
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
Nah et al
-
0.841
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
DeblurGAN-v2
-
0.944
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Uformer-B
36.22
0.957
Uformer: A General U-Shaped Transformer for Image Restoration
DeblurGAN
-
0.903
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
Hu et al
33.67
0.916
Deblurring Low-light Images with Light Streaks
-
MAXIM
35.78
-
MAXIM: Multi-Axis MLP for Image Processing
DeepRFT
36.11
0.955
Intriguing Findings of Frequency Selection for Image Deblurring
MSSNet
35.93
0.953
MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
0 of 19 row(s) selected.
Previous
Next