AI Paper Atlas

Research map / Image generation / Image restoration

I$^2$SB: Image-to-Image Schrödinger Bridge

Guan-Horng Liu, Arash Vahdat, De-An Huang, Evangelos Theodorou, Weili Nie, Anima Anandkumar

ICML 2023 · Image generation › Image restoration · approach: Diffusion-based universal restoration · 15 citations (OpenAlex)

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 Schrödinger bridge from degraded image to clean image (I2SB) instead of Gaussian-noise start (Palette-style conditional diffusion)I2SB vs Palette · JPEG QF=5 and QF=10, inpainting; ImageNet 256FID: e.g. 4.6 vs 8.3 (QF=5)Improved
Use I2SB bridge (no corruption operator knowledge) instead of inverse-problem DIM methodsI2SB vs DDRM/DDNM/PiGDM · nine restoration tasks, ImageNet 256FIDMixed
Replace Schrödinger bridge baseline CDSB with I2SBI2SB vs CDSB · all restoration tasksFIDImproved
Use I2SB with DDPM-style sampling and very few steps (NFE 2-10) instead of Palette with noise priorinpainting Freeform 20-30% · NFE reductionFIDImproved
Deterministic OT-ODE sampling (remove stochasticity from posterior) instead of stochastic posterior sampling (ablation)I2SB on JPEG restoration QF=5 · JPEG QF=5FID difference: +5.3Hurt
Deterministic OT-ODE sampling instead of stochastic posterior sampling (ablation)I2SB on deblurring · Deblurring Uniform and GaussianFID difference: -0.3 (Uniform), -0.6 (Gaussian)Improved
Deterministic OT-ODE sampling instead of stochastic posterior sampling (ablation)I2SB on inpainting with noiseless masks · Inpainting Center and Freeform 20-30%FID difference: +50.9 (Center), +13.0 (Freeform 20-30%)Hurt
Inject Gaussian noise into masked regions of inputs when using OT-ODE (ablation)I2SB OT-ODE on inpainting · Inpainting Center and Freeform 20-30%FID difference: -0.1 (both)No clear effect
Increase mixing of posterior q(Xt|X0,X1) vs forward-SDE marginal as sampling proposal (toward posterior) (ablation)I2SB on JPEG restoration QF=5 · JPEG QF=5FID and CAImproved
Use I2SB with a single network call (NFE=1) instead of Palette with NFE=1 (ablation)inpainting Freeform 20-30% · NFE=1FID-10k: 6.7 vs 19.8Improved
Add conditioning on degraded input X1 to I2SB for general image-to-image translationedges2shoes · Pix2pix tasks, NFE=1000FID: 37.8 vs Pix2pix 73.9Improved

Later papers that compared with this method

7 later accepted papers report I2SB as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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