AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Posterior Samplings are Missing Modalities Generators for Medical Image Translation

Jonghun Kim

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 1 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
use many-to-one instead of many-to-many sampling (all-scenarios training) (ablation)Ours · BraTS T1->T2FID: 65.75 -> 54.15Improved
use many-to-one sampling on full-modal-only trained model (ablation)Ours · BraTS T1->T2PSNR: 22.28 -> 22.19No clear effect
train on all missing-modality scenarios instead of full-modal only (MTO) (ablation)Ours · BraTS T1->T2PSNR: 22.19 -> 23.56Improved
train on all scenarios with MTM sampling instead of full-modal only (ablation)Ours · BraTS T1->T2PSNR: 22.28 -> 22.26No clear effect
use PSLD instead of DPS posterior sampling (ablation)Ours · BraTS T2->T1PSNR: 24.21 -> 25.56Improved
use PSLD instead of FlowDPS (ablation)Ours · BraTS T1->T2PSNR: 22.11 -> 23.56Improved
use PSLD instead of DDNM (ablation)Ours · BraTS T1->T2SSIM: 86.09 -> 88.47Improved
increase number of source modalities from one to three (ablation)Ours · BraTS T1 targetPSNR: 25.56 -> 27.84Improved
replace baselines with posterior-sampled joint priorOurs vs MMHVAE · BraTS T1->T2PSNR: 20.53 -> 23.56Improved
single-source SSIM vs baselinesOurs · BraTS single-sourceSSIM: T1ce->T1: 88.17 vs MMHVAE 89.15Mixed
reduce expectation approximation samples N_EX to 10 -> 1 (ablation)Ours · BraTS tumor segmentationDice: average Dice 76.94% at N_EX=1Hurt
increase N_EX (ablation)Ours · BraTS T1->T2perceptual quality: fidelity up, perceptual quality downHurt

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