# LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling

arXiv: https://arxiv.org/abs/2507.00790 · HTML: https://mlsanity.com/paper/2507.00790/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 10 of its 71 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 10 of 10)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Controlling Vision-Language Models for Multi-Task Image Restoration](https://mlsanity.com/paper/2310.01018/) (2023)
- [ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration](https://mlsanity.com/paper/2306.13653/) (2023)
- [Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization](https://mlsanity.com/paper/2506.17252/) (2025)

## Built on by (most cited first, 9 of 9)

- [Heterogeneous Agent Collaborative Reinforcement Learning](https://mlsanity.com/paper/2603.02604/) (2026)
- [Real-Time Aligned Reward Model beyond Semantics](https://mlsanity.com/paper/2601.22664/) (2026)
- [MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation](https://mlsanity.com/paper/2512.18181/) (2025)
- [From Scale to Speed: Adaptive Test-Time Scaling for Image Editing](https://mlsanity.com/paper/2603.00141/) (2026)
- [OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data](https://mlsanity.com/paper/2606.30019/) (2026)
- [Degradation-Aware Metric Prompting for Hyperspectral Image Restoration](https://mlsanity.com/paper/2512.20251/) (2025)
- [Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment](https://mlsanity.com/paper/2601.22920/) (2026)
- [Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration](https://mlsanity.com/paper/2605.24593/) (2026)
- [EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis](https://mlsanity.com/paper/2606.25465/) (2026)

## Abstract (arXiv)

Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability across various types of degradation, or rely on training with paired datasets, thereby suffering from closed-set constraints. To address these issues, we propose a novel, dataset-free, and unified approach through recurrent posterior sampling utilizing a pretrained latent diffusion model. Our method incorporates the multimodal understanding model to provide sematic priors for the generative model under a task-blind condition. Furthermore, it utilizes a lightweight module to align the degraded input with the generated preference of the diffusion model, and employs recurrent refinement for posterior sampling. Extensive experiments demonstrate that our method outperforms state-of-the-art methods, validating its effectiveness and robustness. Our code and data are available at https://github.com/AMAP-ML/LD-RPS.