RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference

• URL: http://arxiv.org/abs/2604.15459v1
• Date: Thu, 16 Apr 2026 18:18:27 GMT
• Title: RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference
• Abstract summary: Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem.<n>We propose textbfRelativeFlow, a flow matching framework that learns from heterogeneous noisy references.<n>RelativeFlow reformulates flow matching by decomposing the absolute noise-to-clean mapping into relative noisier-to-noisy mappings.
• Score: 11.027227615589247
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem that fundamentally limits denoising performance. Existing simulated-supervised discriminative learning (SimSDL) and simulated-supervised generative learning (SimSGL) treat noisy references as clean targets, causing suboptimal convergence or reference-biased learning, while self-supervised learning (SSL) imposes restrictive noise assumptions that are seldom satisfied in realistic MID scenarios. We propose \textbf{RelativeFlow}, a flow matching framework that learns from heterogeneous noisy references and drives inputs from arbitrary quality levels toward a unified high-quality target. RelativeFlow reformulates flow matching by decomposing the absolute noise-to-clean mapping into relative noisier-to-noisy mappings, and realizes this formulation through two key components: 1) consistent transport (CoT), a displacement map that constrains relative flows to be components of and progressively compose a unified absolute flow, and 2) simulation-based velocity field (SVF), which constructs a learnable velocity field using modality-specific degradation operators to support different medical imaging modalities. Extensive experiments on Computed Tomography (CT) and Magnetic Resonance (MR) denoising demonstrate that RelativeFlow significantly outperforms existing methods, taming MID with noisy references.

Related papers

• Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning [85.93126001283169]
  We introduce Equilibrium Forcing (EqF), a framework for video denoising generative models without noise level conditioning.<n>This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample.
  arXiv  Detail & Related papers  (2026-08-11T00:02:32Z)
• Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy [19.64681328133978]
  Flow matching provides a continuous-time formulation for generative modeling and representation learning.<n>We show that this framework suffers from a fundamental instability in the low-noise regime.<n>We propose Local Contrastive Flow (LCF), a hybrid training protocol that replaces direct velocity regression with contrastive feature alignment at small noise levels.
  arXiv  Detail & Related papers  (2025-09-25T09:36:41Z)
• Score-based Self-supervised MRI Denoising [1.6385815610837167]
  Supervised learning based denoising approaches have achieved impressive performance but require high signal-to-noise ratio (SNR) labels.<n>Self-supervised learning holds promise to address the label scarcity issue, but existing self-supervised denoising methods tend to oversmooth fine spatial features.<n>We introduce Corruption2Self (C2S), a novel score-based self-supervised framework for MRI denoising.
  arXiv  Detail & Related papers  (2025-05-08T20:27:13Z)
• Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement [20.763457281944834]
  Di-Fusion is a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process.<n>Our experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks.
  arXiv  Detail & Related papers  (2025-01-23T10:01:33Z)
• Disentangled Noisy Correspondence Learning [56.06801962154915]
  Cross-modal retrieval is crucial in understanding latent correspondences across modalities. DisNCL is a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning.
  arXiv  Detail & Related papers  (2024-08-10T09:49:55Z)
• Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
  Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast. These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. We first propose a method for estimating the noise level in low light images in a quick and accurate way. We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
  arXiv  Detail & Related papers  (2023-05-17T13:56:48Z)
• Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising [137.5080784570804]
  Video denoising aims at removing noise from videos to recover clean ones. Some existing works show that optical flow can help the denoising by exploiting the additional spatial-temporal clues from nearby frames. We propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels.
  arXiv  Detail & Related papers  (2022-08-25T00:09:18Z)
• Treatment Learning Causal Transformer for Noisy Image Classification [62.639851972495094]
  In this work, we incorporate this binary information of "existence of noise" as treatment into image classification tasks to improve prediction accuracy. Motivated from causal variational inference, we propose a transformer-based architecture, that uses a latent generative model to estimate robust feature representations for noise image classification. We also create new noisy image datasets incorporating a wide range of noise factors for performance benchmarking.
  arXiv  Detail & Related papers  (2022-03-29T13:07:53Z)
• Convolutional Neural Network Denoising in Fluorescence Lifetime Imaging Microscopy (FLIM) [16.558653673949838]
  Fluorescence lifetime imaging microscopy (FLIM) systems are limited by their slow processing speed, low signal-to-noise ratio (SNR), and expensive and challenging hardware setups. In this work, we demonstrate applying a denoising convolutional network to improve FLIM SNR. The network will be integrated with an instant FLIM system with fast data acquisition based on analog signal processing, high SNR using high-efficiency pulse-modulation, and cost-effective implementation utilizing off-the-shelf radio-frequency components.
  arXiv  Detail & Related papers  (2021-03-07T03:27:44Z)
• Residual-driven Fuzzy C-Means Clustering for Image Segmentation [152.609322951917]
  We elaborate on residual-driven Fuzzy C-Means (FCM) for image segmentation. Built on this framework, we present a weighted $ell_2$-norm fidelity term by weighting mixed noise distribution. The results demonstrate the superior effectiveness and efficiency of the proposed algorithm over existing FCM-related algorithms.
  arXiv  Detail & Related papers  (2020-04-15T15:46:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.