Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.
Inception Institute of AI（人工智能起源研究所）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Monash University（莫纳什大学）；University of California, Merced（加州大学默塞德分校）；Yonsei University（延世大学）；Google Research（谷歌研究院）
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural architectures, Transformers, have shown significant performance gains on natural language and high-level vision tasks. While the Transformer model mitigates the shortcomings of CNNs (i.e., limited receptive field and inadaptability to input content), its computational complexity grows quadratically with the spatial resolution, therefore making it infeasible to ap…
Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·泽德人工智能大学）；University of Trento（特伦托大学）；ETH Zürich（苏黎世联邦理工学院）；HKUST (GZ)（香港科技大学（广州））；Peking University（北京大学）；University of California, Merced（加州大学默塞德分校）
IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising
Department of Computer Science, Hanyang University（翰阳大学计算机科学系）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark
Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education（教育部智能计算与信号处理重点实验室（安徽大学））；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）
Since convolutional neural networks perform well in learning generalizable image priors from large-scale data, these models have been widely used in image denoising tasks. However, the computational complexity increases dramatically as well on complex model. In this paper, We propose a novel lightweight Complementary Attention Module, which includes a density module and a sparse module, which can cooperatively mine dense and sparse features for feature complementary learning to build an efficient lightweight architecture. Moreover, to reduce the loss of details caused by denoising, this paper …
For medical image analysis, segmentation models trained on one or several domains lack generalization ability to unseen domains due to discrepancies between different data acquisition policies. We argue that the degeneration in segmentation performance is mainly attributed to overfitting to source domains and domain shift. To this end, we present a novel generalizable medical image segmentation method. To be specific, we design our approach as a multi-task paradigm by combining the segmentation model with a self-supervision domain-specific image restoration (DSIR) module for model regularizati…
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Southern University of Science and Technology（南方科技大学）；StepFun；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳理工大学）
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Macau（澳门大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））
Low-light imaging on mobile devices is typically challenging due to insufficient incident light coming through the relatively small aperture, resulting in a low signal-to-noise ratio. Most of the previous works on low-light image processing focus either only on a single task such as illumination adjustment, color enhancement, or noise removal; or on a joint illumination adjustment and denoising task that heavily relies on short-long exposure image pairs collected from specific camera models, and thus these approaches are less practical and generalizable in real-world settings where camera-spec…
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS部门）；Sangfor Technologies Inc.（Sangfor技术公司）；China Mobile Financial Technology Co., Ltd.（中国移动金融科技有限公司）；CAIR, HKSIS, Chinese Academy of Sciences（中国科学院CAIR、HKSIS部门）；SCSE, FIE, M.U.S.T, Macau, China（澳门SCSE、FIE、M.U.S.T部门）；Vast Intelligence Lab, Sydney, Australia（悉尼澳大利亚Vast Intelligence Lab）
School of Aeronautics and Astronautics, Sichuan University（四川大学航空航天学院）；University of Electronic Science and Technology of China（电子科技大学）；College of Electronics and Information Engineering, Sichuan University（四川大学电子信息工程学院）
Universidad Politécnica de Madrid（马德里理工大学）；Centre national de la recherche scientifique (CNRS)（法国国家科学研究中心）；Interdisciplinary Institute for Neuroscience (IINS)（跨学科神经科学研究所）；University of Bordeaux（波尔多大学）；Mechanobiology Institute（机械生物学研究所）；National University of Singapore（新加坡国立大学）
Microscopy images often suffer from high levels of noise, which can hinder further analysis and interpretation. Content-aware image restoration (CARE) methods have been proposed to address this issue, but they often require large amounts of training data and suffer from over-fitting. To overcome these challenges, we propose a novel framework for few-shot microscopy image denoising. Our approach combines a generative adversarial network (GAN) trained via contrastive learning (CL) with two structure preserving loss terms (Structural Similarity Index and Total Variation loss) to further improve t…
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；CUHK MMLab（香港中文大学多媒体实验室）；CPII under InnoHK（创新香港研究院下的CPII）；Tsinghua University（清华大学）
