AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Backward SDE–Based Diffusion for Physics-Constrained Generation

Zihao WANG

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling

Read the paper

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 hard terminal constraint instead of soft terminal penalty (ablation)BSDE solver · 128x128 CT reconstructionPSNR: 33.10 -> 35.36Improved
use hard terminal constraint instead of soft terminal penalty (ablation)BSDE solver · 128x128 CT reconstructionRelative measurement residual: 0.00203 -> 0.00128Improved
add BSDE correction network with terminal constraint (ablation)BSDE solver · 128x128 CT reconstructionPSNR: 17.38 -> 35.36Improved
add BSDE correction network with terminal constraint (ablation)BSDE solver · 128x128 CT reconstructionSSIM: 0.4188 -> 0.9460Improved
add BSDE correction network with terminal constraint (ablation)BSDE solver · 128x128 CT reconstructionRelative measurement residual: 0.2008 -> 0.00128Improved
set terminal timepoint tau 0.15 instead of 0.05 (ablation)BSDE solver · 128x128 CT reconstructionPSNR: 35.52 -> 35.21No clear effect
raise terminal timepoint tau from 0.15 to 0.35 (ablation)BSDE solver · 128x128 CT reconstructionPSNR: 35.21 -> 31.34Hurt
raise terminal timepoint tau from 0.35 to 0.45 (ablation)BSDE solver · 128x128 CT reconstructionPSNR: 31.34 -> 23.48Hurt
use BSDE terminal conditioning instead of TVDIPSVCT reconstruction · SVCTMAE: 4.56 -> 3.57Improved
use BSDE terminal conditioning instead of FBPSVCT reconstruction · SVCTSSIM: 0.366 -> 0.868Improved
use BSDE instead of DDS (CT-domain prior) on PSNRSVCT reconstruction · SVCTPSNR: 31.10 -> 30.99Hurt
use BSDE instead of SDE-diffusion perturbation editing for Cepheidstar lightcurve generation · Star lightcurves (Cepheid)Average cosine similarity: 0.4338 -> 0.7095Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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