Learning to Recorrupt (L2R)

Noise distribution agnostic self-supervised image denoising.

Brayan Monroy · Jorge Bacca · Julian Tachella

Paper · Code · Weights

L2R jointly learns a denoiser and a monotonic recorruptor using noisy images alone.

Weights

Eight RGB DRUNet checkpoints cover log-gamma, Laplace, correlated Gaussian, Poisson–Gaussian, and Poisson noise. manifest.json contains their settings and SHA-256 hashes. mfcn_init.pth initializes the monotonic network as a Gaussian identity map.

Use

From the code repository, with dependencies installed and test caches available:

hf download bemc22/learning2recorrupt --local-dir pretrained
python test.py --checkpoint-dir pretrained

Citation

@article{monroy2026learning,
  title={Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising},
  author={Monroy, Brayan and Bacca, Jorge and Tachella, Juli{\'a}n},
  journal={arXiv preprint arXiv:2603.25869},
  year={2026}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for bemc22/learning2recorrupt