HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Deblurring On Hide Trained On Gopro

Metrics

PSNR (sRGB)
Params (M)
SSIM (sRGB)

Results

Performance results of various models on this benchmark

Paper Title
MAXIM32.8322.20.956MAXIM: Multi-Axis MLP for Image Processing
AdaRevD32.35-0.953AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
ID-Blau (FFTformer)31.94-0.949ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
CAPTNet31.86-0.949Prompt-based Ingredient-Oriented All-in-One Image Restoration
LoFormer31.86-0.949LoFormer: Local Frequency Transformer for Image Deblurring
DeepRFT+31.66-0.946Intriguing Findings of Frequency Selection for Image Deblurring
ID-Blau (Restormer)31.66-0.947ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
FFTformer31.6216.60.9455Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
LaKDNet31.5837.50.946Revisiting Image Deblurring with an Efficient ConvNet
ID-Blau (Stripformer)31.50-0.944ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
Restormer-TLC31.4926.130.945Improving Image Restoration by Revisiting Global Information Aggregation
DeblurDiNAT-L31.4716.10.944DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains
Restormer31.2226.130.942Restormer: Efficient Transformer for High-Resolution Image Restoration
MPRNet-TLC31.1920.10.942Improving Image Restoration by Revisiting Global Information Aggregation
Stripformer31.03-0.94Stripformer: Strip Transformer for Fast Image Deblurring
MPRNet30.9620.10.939Multi-Stage Progressive Image Restoration
Uformer-B30.8350.880.952Uformer: A General U-Shaped Transformer for Image Restoration
BANet30.16-0.93BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
Suin et al29.98-0.930-
MT-RNN29.152.60.918Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training
0 of 25 row(s) selected.