Median2Median: Zero-shot Suppression of Structured Noise in Images
Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to remove. Most data-driven approaches rely on large datasets with high-quality labels and still suffer from limited generalizability, whereas existing zero-shot methods avoid this limitation but remain effective only for independent and identically distributed (i.i.d.) noise. To address this gap, we propose Median2Median (M2M), a zero-shot denoising framework designed for structured noise. M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input. This strategy leverages directional interpolation and generalized median filtering to adaptively exclude values distorted by structured artifacts. To further enlarge the effective sampling space and eliminate systematic bias, a randomized assignment strategy is employed, ensuring that the sampled sub-image pairs are suitable for Noise2Noise training. In our realistic simulation studies, M2M performs on par with state-of-the-art zero-shot methods under i.i.d. noise, while consistently outperforming them under correlated noise. These findings establish M2M as an efficient, data-free solution for structured noise suppression and mark the first step toward effective zero-shot denoising beyond the strict i.i.d. assumption.
Code (0)
등록된 구현이 없습니다.
Tasks
Image DenoisingSimilar Papers 제목 키워드 기반
Using Large Language Models to Measure Symptom Severity in Patients At Risk for Schizophrenia
Patients who are at clinical high risk (CHR) for schizophrenia need close monitoring of their symptoms to inform appropriate treatments. The Brief Psychiatric Rating Scale (BPRS) is a validated, commonly used research to…
Few-Shot LearningA Total Variation Denoising Method Based on Median Filter and Phase Consistency
The total variation method is widely used in image noise suppression. However, this method is easy to cause the loss of image details, and it is also sensitive to parameters such as iteration time. In this work, the tota…
DenoisingMonolingual Adapters for Zero-Shot Neural Machine Translation
We propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific to one la…
Machine TranslationTranslationOptimal Privacy-Preserving Distributed Median Consensus
Distributed median consensus has emerged as a critical paradigm in multi-agent systems due to the inherent robustness of the median against outliers and anomalies in measurement. Despite the sensitivity of the data invol…
Privacy PreservingMC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning
Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout b…
Reinforcement Learning