相关论文: RIRF: Reasoning Image Restoration Framework

Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradation may lead to poor…

All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often fail to explicitly model degradation types and struggle to adapt their…

Despite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being applied to real-world usages: (1) the lack of generalization…

Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through…

Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting…

Existing medical image restoration (Med-IR) methods are typically modality-specific or degradation-specific, failing to generalize across the heterogeneous degradations encountered in clinical practice. We argue this limitation stems from…

Visual images corrupted by various types and levels of degradations are commonly encountered in practical image compression. However, most existing image compression methods are tailored for clean images, therefore struggling to achieve…

Intrinsic image decomposition aims to separate images into physical components such as albedo, depth, normals, and illumination. While recent diffusion- and transformer-based models benefit from paired supervision from synthetic datasets,…

In reality, images often exhibit multiple degradations, such as rain and fog at night (triple degradations). However, in many cases, individuals may not want to remove all degradations, for instance, a blurry lens revealing a beautiful…

Deep unfolding networks (DUNs) are widely employed in illumination degradation image restoration (IDIR) to merge the interpretability of model-based approaches with the generalization of learning-based methods. However, the performance of…

Underwater Image Restoration (UIR) remains a challenging task in computer vision due to the complex degradation of images in underwater environments. While recent approaches have leveraged various deep learning techniques, including…

The growing integration of vision-language models (VLMs) in medical applications offers promising support for diagnostic reasoning. However, current medical VLMs often face limitations in generalization, transparency, and computational…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

Image captioning models often suffer from performance degradation when applied to novel datasets, as they are typically trained on domain-specific data. To enhance generalization in out-of-domain scenarios, retrieval-augmented approaches…

Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense reasoning tasks, often exhibiting a lack of "deliberative…

Automatic radiology report generation has attracted enormous research interest due to its practical value in reducing the workload of radiologists. However, simultaneously establishing global correspondences between the image (e.g., Chest…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands, rendering them unsuitable for deployment on edge devices.…

While vision transformers show promise in numerous image restoration (IR) tasks, the challenge remains in efficiently generalizing and scaling up a model for multiple IR tasks. To strike a balance between efficiency and model capacity for a…

Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improvements through simulating those degradations and leveraging…