# Implicit Image-to-Image Schrodinger Bridge for Image Restoration

Source: [Implicit Image-to-Image Schrodinger Bridge for Image Restoration](<https://www.sota2.com/research/paper/68fa77971e209131cea7434d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:22:38.768Z

Authors: Yuang Wang, Siyeop Yoon, Pengfei Jin, Matthew Tivnan, Sifan Song, Zhennong Chen, Rui Hu, Li Zhang, Quanzheng Li, Zhiqiang Chen, Dufan Wu

Published: 2024-03-10T03:22:57.000Z

## Abstract

Diffusion-based models have demonstrated remarkable effectiveness in image restoration tasks; however, their iterative denoising process, which starts from Gaussian noise, often leads to slow inference speeds. The Image-to-Image Schr\\"odinger Bridge (I$^2$SB) offers a promising alternative by initializing the generative process from corrupted images while leveraging training techniques from score-based diffusion models. In this paper, we introduce the Implicit Image-to-Image Schr\\"odinger Bridge (I$^3$SB) to further accelerate the generative process of I$^2$SB. I$^3$SB restructures the generative process into a non-Markovian framework by incorporating the initial corrupted image at each generative step, effectively preserving and utilizing its information. To enable direct use of pretrained I$^2$SB models without additional training, we ensure consistency in marginal distributions. Extensive experiments across many image corruptions, including noise, low resolution, JPEG compression, and sparse sampling, and multiple image modalities, such as natural, human face, and medical images, demonstrate the acceleration benefits of I$^3$SB. Compared to I$^2$SB, I$^3$SB achieves the same perceptual quality with fewer generative steps, while maintaining or improving fidelity to the ground truth.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Super-Resolution on ImageNet 256x256 noiseless 4x SR (test)](<https://www.sota2.com/research/sota/image-super-resolution-on-imagenet-256x256-noiseless-4x-sr-test.md>): Image Super-resolution; ImageNet 256x256 noiseless 4x SR (test); PSNR: 25.24.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.06069>)

[PDF](<https://arxiv.org/pdf/2403.06069.pdf>)