Downloads · 30 days
0
denoise-sr-baseline
tannu1632/denoise-sr-baseline
denoise-sr-baseline is a image-to-image model from tannu1632. Use it when you need one image transformed into another. The card lists the license as mit.
Residual CNN + PixelShuffle upsampler that denoises low-light images and upscales them 4x. Trained end-to-end with L1 loss on paired noisy-LR / clean-HR images from the DLP 26T2 NPPE3 competition dataset.
Access
Public
Updated Sep 6, 2026
Repo size
4.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth4.9 MB · 100%
At a glance
- Task
- Image-to-Image
- License
- mit
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- d809aa62
Model card
From the Hugging Face model README
Low-Light Denoising + 4x Super-Resolution
Residual CNN + PixelShuffle upsampler that denoises low-light images and upscales them 4x. Trained end-to-end with L1 loss on paired noisy-LR / clean-HR images from the DLP 26T2 NPPE3 competition dataset.
- Scale: 4x
- Architecture: 12 residual blocks, 64 base channels, PixelShuffle upsampler
- Params: 1.22M
- Val PSNR: 38.53 dB (best, epoch 27/40)
- Train/Val pairs: 1105 / 267
- Framework: PyTorch
Training
- Loss: L1
- Optimizer: Adam, lr=2e-4, cosine annealing
- Epochs: 40
- Batch size: 16
- Patch size: 48 (LR) → 192 (HR)
Usage
import torch
from model import DenoiseSRNet
model = DenoiseSRNet(base_ch=64, n_blocks=12, scale=4)
model.load_state_dict(torch.load("best_model.pth", map_location="cpu"))
model.eval()
Limitations
Trained on a specific low-light dataset — may not generalize to other scale factors, noise levels, or daytime images.
- Task
- Image-to-Image
- License
- mit
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026