AI Paper Atlas

Research map / Image generation / Editing and style transfer

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Clément Chadebec, Onur Tasar, Sanjeev Sreetharan, Benjamin Aubin

ICCV 2025 · Image generation › Editing and style transfer · approach: Image-to-image translation · 33 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
raise pixel loss weight from 1 to 10 (ablation)LBM · RORD object removalFID: 30.21 -> 26.70Improved
raise pixel loss weight from 10 to 20 (ablation)LBM · RORD object removalFID: 26.70 -> 27.09No clear effect
raise pixel loss weight from 1 to 10 (ablation)LBM · RORD object removalPSNR: 22.55 -> 22.39Hurt
add noise sigma (stochastic bridge) instead of flow matching, small sigma (ablation)LBM · RORD object removalFIDImproved
use too large sigma (ablation)LBM · RORD object removalFIDHurt
use 4 discrete timesteps instead of uniform timestep distribution (ablation)LBM · RORD object removalFIDImproved
increase inference steps beyond 4 with discrete timestep training (ablation)LBM · RORD object removalFIDHurt
pretrained initialization instead of training from scratch (ablation)LBM · RORD object removal (coarse masks)FID: 27.9 -> 26.9Improved
add synthetic rendered data to relighting training (ablation)LBM · Image relightingFIDImproved
use too much synthetic data (ablation)LBM · Image relightingFIDHurt
operate in latent space instead of pixel space (1024 resolution) (ablation)bridge model · Inference latencylatency: 20.11 -> 0.27Improved
operate in latent space instead of pixel space (training, 256) (ablation)bridge model · Training peak memorypeak memory (GB): 43.19 -> 24.85Improved

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