AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Optimal transport unlocks end-to-end learning for single-molecule localization

Romain Seailles, Jean Baptiste Masson, Jean Ponce, Julien Mairal

ICLR 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 0 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 optimal-transport loss to DECODE architecture (ablation)DECODE · EPFL 2016 SMLM (density 2.0, high SNR)E3D: 0.705 -> 0.740Improved
add iterative refinement architecture on top of OT loss (ablation)OT-loss model · EPFL 2016 SMLM (density 2.0, high SNR)E3D: 0.740 -> 0.750Improved
add iterative architecture with DECODE loss (ablation)DECODE loss · EPFL 2016 SMLM (density 2.0, high SNR)E3D: 0.705 -> 0.703No clear effect
use CNN decoder instead of ViT decoder (ablation)Ours (d=HW/4) · MT0N1HDASE3D: 0.722 -> 0.750Improved
reduce candidates from HW to HW/4 (ablation)CNN decoder · MT0N1HDASE3D: 0.732 -> 0.750Improved
reduce candidates from HW/4 to HW/16 (ablation)CNN decoder · MT0N1HDASE3D: 0.750 -> 0.739Hurt
increase Sinkhorn epsilon from 1e-4 to 1e-2 (ablation)OT loss · MT0N1HDASE3D: 0.750 -> 0.397Hurt
lower epsilon from 1e-3 to 1e-4 (ablation)OT loss · MT0N1HDASE3D: 0.739 -> 0.750Improved
lower epsilon from 1e-4 to 1e-5 (ablation)OT loss · MT0N1HDASE3D: 0.750 -> 0.747No clear effect
use Sinkhorn regularized OT instead of Hungarian matching (ablation)OT loss · MT0N1HDASE3D: 0.742 -> 0.750Improved
increase camera parameter jitter from sigma 0 to 0.30 at test time (ablation)Ours · EPFL synthetic density 2.0 (camera mismatch)E3D: 0.811 -> 0.805No clear effect
use OT loss and iterative arch vs LiteLoc under binning x32Ours vs LiteLoc · Real NPC-Nup96 x32FRC (nm): 71.5 -> 44.2Improved

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