One-Step Is Optimal: Unconditional Rectified Flows are Noise2Noise Denoisers, and Multi-Step Integration Provably Hurts---A Benchmark and Task-Based Detectability Study on Low-Dose CT

arXiv:2609.31670 · cs.CV · Submitted 2026-09-15 · Read on arXiv

cs.CV

Submitted: 2026-09-15

Updated: 2026-09-15

Terminology

• Benchmark — 30× in this paper · explained in 2 episodes
• Hallucination — 14× in this paper · explained in 3 episodes
• Rectified Flow — 12× in this paper · explained in 3 episodes
• Fidelity — 11× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Flow Matching — 5× in this paper · explained in 8 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Channelized Hotelling Observer — 4× in this paper
• Conditional Flow Matching — 3× in this paper
• Model-Agnostic — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Gradient Magnitude Similarity Deviation — 2× in this paper
• In Medical Image Computing and Computer-Assisted Intervention — 2× in this paper
• Poisson Flow Consistency Models — 2× in this paper
• Residual Spectral Ratio — 2× in this paper
• AUC — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Normalizing Flow — 1× in this paper · explained in 3 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes

Sources

• The Generation Phases of Flow Matching: a Denoising Perspective
• Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
• Suppression of Correlated Noise with Similarity-based Unsupervised Deep Learning
• Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising
• Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models