# DNA-Prior: Unsupervised Denoise Anything via Dual-Domain Prior

arXiv: https://arxiv.org/abs/2511.23124 · HTML: https://mlsanity.com/paper/2511.23124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [Image Restoration using Total Variation Regularized Deep Image Prior](https://mlsanity.com/paper/1810.12864/) (2018)
- [Deep Spectral Prior](https://mlsanity.com/paper/2505.19873/) (2025)

## Abstract (arXiv)

Medical imaging pipelines critically rely on robust denoising to stabilise downstream tasks such as segmentation and reconstruction. However, many existing denoisers depend on large annotated datasets or supervised learning, which restricts their usability in clinical environments with heterogeneous modalities and limited ground-truth data. To address this limitation, we introduce DNA-Prior, a universal unsupervised denoising framework that reconstructs clean images directly from corrupted observations through a mathematically principled hybrid prior. DNA-Prior integrates (i) an implicit architectural prior, enforced through a deep network parameterisation, with (ii) an explicit spectral-spatial prior composed of a frequency-domain fidelity term and a spatial regularisation functional. This dual-domain formulation yields a well-structured optimisation problem that jointly preserves global frequency characteristics and local anatomical structure, without requiring any external training data or modality-specific tuning. Experiments across multiple modalities show that DNA achieves consistent noise suppression and structural preservation under diverse noise conditions.