Downloads · 30 days
0
nppe3-denoise-sr
aganjali/nppe3-denoise-sr
nppe3-denoise-sr is a machine learning model from aganjali. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Residual CNN (SRResNet-style residual blocks + PixelShuffle upsampling, MPRNet-style residual/skip formulation), trained with a Charbonnier loss for a PSNR-graded low-light denoising + 4x super-resolution task.
Access
Public
Updated Sep 7, 2026
Repo size
43.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin8.3 MB · 100%
At a glance
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 7, 2026
- SHA
- 60cb3391
Model card
From the Hugging Face model README
DenoiseSRNet — NPPE-3 (Low-light denoising + 4x super-resolution)
Residual CNN (SRResNet-style residual blocks + PixelShuffle upsampling, MPRNet-style residual/skip formulation), trained with a Charbonnier loss for a PSNR-graded low-light denoising + 4x super-resolution task.
- Scale: 4x
- Best validation PSNR: 39.03 dB
- Params: 2.06M
- Created
- Sep 6, 2026
- Updated
- Sep 7, 2026