# MID: A Self-supervised Multimodal Iterative Denoising Framework

arXiv: https://arxiv.org/abs/2511.00997 · HTML: https://mlsanity.com/paper/2511.00997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 71 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models](https://mlsanity.com/paper/2302.03018/) (2023)
- [DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization](https://mlsanity.com/paper/2211.10682/) (2022)
- [High-Frequency Space Diffusion Models for Accelerated MRI](https://mlsanity.com/paper/2208.05481/) (2022)
- [CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus](https://mlsanity.com/paper/2001.02643/) (2020)
- [A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noise](https://mlsanity.com/paper/2205.10278/) (2022)
- [MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network](https://mlsanity.com/paper/2304.01598/) (2023)
- [Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning](https://mlsanity.com/paper/2011.01355/) (2020)
- [M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising](https://mlsanity.com/paper/2406.02263/) (2024)
- [Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling](https://mlsanity.com/paper/2307.03992/) (2023)
- [Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network](https://mlsanity.com/paper/2304.09507/) (2023)
- [IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising](https://mlsanity.com/paper/2508.19649/) (2025)
- [Adaptive Image Denoising by Targeted Databases](https://mlsanity.com/paper/1407.5055/) (2014)
- [MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training](https://mlsanity.com/paper/2406.05347/) (2024)
- [PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus](https://mlsanity.com/paper/2401.14919/) (2024)
- [TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement](https://mlsanity.com/paper/2410.03843/) (2024)
- [Positive2Negative: Breaking the Information-Lossy Barrier in Self-Supervised Single Image Denoising](https://mlsanity.com/paper/2412.16460/) (2024)
- [SDEMG: Score-based Diffusion Model for Surface Electromyographic Signal Denoising](https://mlsanity.com/paper/2402.03808/) (2024)

## Abstract (arXiv)

Data denoising is a persistent challenge across scientific and engineering domains. Real-world data is frequently corrupted by complex, non-linear noise, rendering traditional rule-based denoising methods inadequate. To overcome these obstacles, we propose a novel self-supervised multimodal iterative denoising (MID) framework. MID models the collected noisy data as a state within a continuous process of non-linear noise accumulation. By iteratively introducing further noise, MID learns two neural networks: one to estimate the current noise step and another to predict and subtract the corresponding noise increment. For complex non-linear contamination, MID employs a first-order Taylor expansion to locally linearize the noise process, enabling effective iterative removal. Crucially, MID does not require paired clean-noisy datasets, as it learns noise characteristics directly from the noisy inputs. Experiments across four classic computer vision tasks demonstrate MID's robustness, adaptability, and consistent state-of-the-art performance. Moreover, MID exhibits strong performance and adaptability in tasks within the biomedical and bioinformatics domains.