AI RESEARCH
RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference
arXiv CS.AI
•
ArXi:2604.15459v1 Announce Type: cross 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.