AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples

Haoye Lu, Yaoliang Yu, Darren Lo

ICLR 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 50 clean samples as prior to SFBD-OMNI under additive Gaussian noise (ablation)SFBD-OMNI · CIFAR-10 additive GaussianFID: 80.37 -> 10.81Improved
keep clean samples active as soft prior when corruption is non-identifiable (ablation)Online SFBD-OMNI · CelebA grayscale and Gaussian blurFIDImproved
use clean-sample weight in identifiable corruption (Gaussian noise) (ablation)Online SFBD-OMNI · CIFAR-10 additive GaussianFIDHurt
overly large clean-sample weight in non-identifiable corruption (ablation)Online SFBD-OMNI · non-identifiable corruptionsFIDHurt
increase number of clean samples (ablation)Online SFBD-OMNI · CelebA grayscaleFIDImproved
larger update ratio gamma (0.5) (ablation)Online SFBD-OMNI · CIFAR-10 additive Gaussian (sigma=0.5)FIDMixed
SFBD-OMNI instead of EMDiffusionEMDiffusion · CIFAR-10 pixel maskingFID: 21.08 -> 21.31No clear effect
SFBD-OMNI instead of SFBDSFBD · CIFAR-10 additive GaussianFID: 13.53 -> 10.81Improved
online variant instead of classical SFBD-OMNISFBD-OMNI · identifiable corruptions (CIFAR-10 masking, Gaussian)FID: 21.31 -> 22.43; 10.81 -> 11.06Hurt
online variant instead of classical SFBD-OMNISFBD-OMNI · non-identifiable corruptions (CIFAR-10 grayscale, CelebA blur, grayscale)FID: 32.61 -> 31.32; 11.60 -> 10.28; 11.85 -> 11.21Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy