Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DeblurDiNAT-L

DeblurDiNAT-L

Reported on 36 benchmarks across 4 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision9 results

DeblurringonRealBlur-J (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.885
best: 0.894 (AdaRevD)
SOTA
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonGoPro
PSNR· 2024-03-19
33.63
best: 35.98 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonGoPro
SSIM· 2024-03-19
0.967
best: 0.9792 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonRealBlur-R (trained on GoPro)
PSNR (sRGB)· 2024-03-19
36.09
best: 36.53 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonRealBlur-R (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.955
best: 0.961 (ALGNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonRealBlur-J (trained on GoPro)
PSNR (sRGB)· 2024-03-19
28.98
best: 30.12 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonHIDE (trained on GOPRO)
PSNR (sRGB)· 2024-03-19
31.47
best: 32.83 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonHIDE (trained on GOPRO)
Params (M)· 2024-03-19
16.1
best: 50.88 (Uformer-B)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
DeblurringonHIDE (trained on GOPRO)
SSIM (sRGB)· 2024-03-19
0.944
best: 0.956 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163

Methodology9 results

2D ClassificationonRealBlur-J (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.885
best: 0.894 (AdaRevD)
SOTA
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonGoPro
PSNR· 2024-03-19
33.63
best: 35.98 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonGoPro
SSIM· 2024-03-19
0.967
best: 0.9792 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonRealBlur-R (trained on GoPro)
PSNR (sRGB)· 2024-03-19
36.09
best: 36.53 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonRealBlur-R (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.955
best: 0.961 (ALGNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonRealBlur-J (trained on GoPro)
PSNR (sRGB)· 2024-03-19
28.98
best: 30.12 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonHIDE (trained on GOPRO)
PSNR (sRGB)· 2024-03-19
31.47
best: 32.83 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonHIDE (trained on GOPRO)
Params (M)· 2024-03-19
16.1
best: 50.88 (Uformer-B)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
2D ClassificationonHIDE (trained on GOPRO)
SSIM (sRGB)· 2024-03-19
0.944
best: 0.956 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163

Audio9 results

10-shot image generationonRealBlur-J (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.885
best: 0.894 (AdaRevD)
SOTA
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonGoPro
PSNR· 2024-03-19
33.63
best: 35.98 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonGoPro
SSIM· 2024-03-19
0.967
best: 0.9792 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonRealBlur-R (trained on GoPro)
PSNR (sRGB)· 2024-03-19
36.09
best: 36.53 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonRealBlur-R (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.955
best: 0.961 (ALGNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonRealBlur-J (trained on GoPro)
PSNR (sRGB)· 2024-03-19
28.98
best: 30.12 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonHIDE (trained on GOPRO)
PSNR (sRGB)· 2024-03-19
31.47
best: 32.83 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonHIDE (trained on GOPRO)
Params (M)· 2024-03-19
16.1
best: 50.88 (Uformer-B)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
10-shot image generationonHIDE (trained on GOPRO)
SSIM (sRGB)· 2024-03-19
0.944
best: 0.956 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163

Computer Code9 results

Blind Image DeblurringonRealBlur-J (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.885
best: 0.894 (AdaRevD)
SOTA
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonGoPro
PSNR· 2024-03-19
33.63
best: 35.98 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonGoPro
SSIM· 2024-03-19
0.967
best: 0.9792 (BSSTNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonRealBlur-R (trained on GoPro)
PSNR (sRGB)· 2024-03-19
36.09
best: 36.53 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonRealBlur-R (trained on GoPro)
SSIM (sRGB)· 2024-03-19
0.955
best: 0.961 (ALGNet)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonRealBlur-J (trained on GoPro)
PSNR (sRGB)· 2024-03-19
28.98
best: 30.12 (AdaRevD)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonHIDE (trained on GOPRO)
PSNR (sRGB)· 2024-03-19
31.47
best: 32.83 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonHIDE (trained on GOPRO)
Params (M)· 2024-03-19
16.1
best: 50.88 (Uformer-B)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163
Blind Image DeblurringonHIDE (trained on GOPRO)
SSIM (sRGB)· 2024-03-19
0.944
best: 0.956 (MAXIM)
DeblurDiNAT: A Compact Model with Exceptional Generalization and Visual Fidelity on Unseen Domains arXiv:2403.13163