RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

• URL: http://arxiv.org/abs/2603.25502v1
• Date: Thu, 26 Mar 2026 14:39:39 GMT
• Title: RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
• Abstract summary: We construct a large-scale dataset covering nine common real-world degradation types.<n>We train a state-of-the-art open-source model to narrow the gap with closed-source alternatives.<n>Our model ranks first among open-source methods, achieving state-of-the-art performance.
• Score: 55.40883650570416
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image restoration under real-world degradations is critical for downstream tasks such as autonomous driving and object detection. However, existing restoration models are often limited by the scale and distribution of their training data, resulting in poor generalization to real-world scenarios. Recently, large-scale image editing models have shown strong generalization ability in restoration tasks, especially for closed-source models like Nano Banana Pro, which can restore images while preserving consistency. Nevertheless, achieving such performance with those large universal models requires substantial data and computational costs. To address this issue, we construct a large-scale dataset covering nine common real-world degradation types and train a state-of-the-art open-source model to narrow the gap with closed-source alternatives. Furthermore, we introduce RealIR-Bench, which contains 464 real-world degraded images and tailored evaluation metrics focusing on degradation removal and consistency preservation. Extensive experiments demonstrate our model ranks first among open-source methods, achieving state-of-the-art performance.

Related papers

• UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration [20.447922377156143]
  Universal image restoration aims to recover clean images from arbitrary real-world degradations.<n>Existing all-in-one restoration networks do not scale to multiple degradations.<n>We introduce a unified inference pipeline with a mixture-of-experts architecture that decomposes restoration knowledge across specialized task-adaptable experts.
  arXiv  Detail & Related papers  (2026-03-08T01:35:54Z)
• UniSER: A Foundation Model for Unified Soft Effects Removal [72.60782767314713]
  We introduce UniSER, capable of addressing diverse degradations caused by soft effects within a single framework.<n>Our methodology centers on curating a massive 3.8M-pair dataset to ensure robustness and generalization.<n>This synergistic approach allows UniSER to significantly outperform both specialist and generalist models.
  arXiv  Detail & Related papers  (2025-11-18T06:39:39Z)
• Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content [53.93606081932928]
  We introduce a novel black box detection framework that requires only API access.<n>We measure the likelihood that the image was generated by the model itself.<n>For black-box models that do not support masked image inputs, we incorporate a cost efficient surrogate model trained to align with the target model distribution.
  arXiv  Detail & Related papers  (2025-05-02T05:11:35Z)
• Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation [158.37640586809187]
  Restoring any degraded image efficiently via just one model has become increasingly significant.<n>Our approach, termed AnyIR, takes a unified path that leverages inherent similarity across various degradations.<n>To fuse the degradation awareness and the contextualized attention, a spatial-frequency parallel fusion strategy is proposed.
  arXiv  Detail & Related papers  (2025-04-19T09:54:46Z)
• FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration [66.61201445650323]
  Existing methods suffer from a generalization bottleneck in real-world scenarios.<n>We contribute a million-scale dataset with two notable advantages over existing training data.<n>We propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios.
  arXiv  Detail & Related papers  (2024-12-02T12:08:40Z)
• Towards Realistic Data Generation for Real-World Super-Resolution [58.99206459754721]
  RealDGen is an unsupervised learning data generation framework designed for real-world super-resolution.<n>We develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model.<n>Experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations.
  arXiv  Detail & Related papers  (2024-06-11T13:34:57Z)
• A general approach to bridge the reality-gap [0.0]
  A common approach to circumvent this is to leverage existing, similar data-sets with large amounts of labelled data. We propose learning a general transformation to bring arbitrary images towards a canonical distribution. This transformation is trained in an unsupervised regime, leveraging data augmentation to generate off-canonical examples of images.
  arXiv  Detail & Related papers  (2020-09-03T18:19:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.