# AsyncDSB: Schedule-Asynchronous Diffusion Schr"odinger Bridge for Image Inpainting

arXiv: https://arxiv.org/abs/2412.08149 · HTML: https://mlsanity.com/paper/2412.08149/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 37 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 4 of 4)

- [On the Importance of Noise Scheduling for Diffusion Models](https://mlsanity.com/paper/2301.10972/) (2023)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2403.19898/) (2024)
- [An analysis of the noise schedule for score-based generative models](https://mlsanity.com/paper/2402.04650/) (2024)

## Built on by (most cited first, 3 of 3)

- [When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration](https://mlsanity.com/paper/2509.17024/) (2025)
- [Improved Masked Image Generation with Knowledge-Augmented Token Representations](https://mlsanity.com/paper/2511.12032/) (2025)
- [GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors](https://mlsanity.com/paper/2608.12203/) (2026)

## Abstract (arXiv)

Image inpainting is an important image generation task, which aims to restore corrupted image from partial visible area. Recently, diffusion Schr"odinger bridge methods effectively tackle this task by modeling the translation between corrupted and target images as a diffusion Schr"odinger bridge process along a noising schedule path. Although these methods have shown superior performance, in this paper, we find that 1) existing methods suffer from a schedule-restoration mismatching issue, i.e., the theoretical schedule and practical restoration processes usually exist a large discrepancy, which theoretically results in the schedule not fully leveraged for restoring images; and 2) the key reason causing such issue is that the restoration process of all pixels are actually asynchronous but existing methods set a synchronous noise schedule to them, i.e., all pixels shares the same noise schedule. To this end, we propose a schedule-Asynchronous Diffusion Schr"odinger Bridge (AsyncDSB) for image inpainting. Our insight is preferentially scheduling pixels with high frequency (i.e., large gradients) and then low frequency (i.e., small gradients). Based on this insight, given a corrupted image, we first train a network to predict its gradient map in corrupted area. Then, we regard the predicted image gradient as prior and design a simple yet effective pixel-asynchronous noise schedule strategy to enhance the diffusion Schr"odinger bridge. Thanks to the asynchronous schedule at pixels, the temporal interdependence of restoration process between pixels can be fully characterized for high-quality image inpainting. Experiments on real-world datasets show that our AsyncDSB achieves superior performance, especially on FID with around 3% - 14% improvement over state-of-the-art baseline methods.