Related papers: Hallucination Index: An Image Quality Metric for G…
Generative super-resolution (GSR) currently sets the state-of-the-art in terms of perceptual image quality, overcoming the "regression-to-the-mean" blur of prior non-generative models. However, from a human perspective, such models do not…
Generative models are prone to hallucinations: plausible but incorrect structures absent in the ground truth. This issue is problematic in image restoration for safety-critical domains such as medical imaging, industrial inspection, and…
Generative models are increasingly used to improve the quality of medical imaging, such as reconstruction of magnetic resonance images and computed tomography. However, it is well-known that such models are susceptible to hallucinations:…
Tomographic image reconstruction is generally an ill-posed linear inverse problem. Such ill-posed inverse problems are typically regularized using prior knowledge of the sought-after object property. Recently, deep neural networks have been…
Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis. However, they still often produce hallucinated samples (hallucinations) that conflict with real-world…
Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to…
This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference. The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse…
Recent developments in diffusion models have advanced conditioned image generation, yet they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in medical images, causing "image hallucination" and risking…
While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To…
Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their…
Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as hallucinations. Effectively detecting hallucinations is therefore crucial for the safe deployment of LLMs. Recent research has linked…
Hallucinations are spurious structures not present in the ground truth, posing a critical challenge in medical image reconstruction, especially for data-driven conditional models. We hypothesize that combining an unconditional diffusion…
No-reference image quality assessment (NR-IQA) is a fundamental yet challenging task in low-level computer vision community. The difficulty is particularly pronounced for the limited information, for which the corresponding reference for…
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These…
In recent studies, the extensive utilization of large language models has underscored the importance of robust evaluation methodologies for assessing text generation quality and relevance to specific tasks. This has revealed a prevalent…
Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit "hallucinations," samples that could never occur in the training data. But where do such hallucinations come from? In this paper,…
Score-based diffusion models have achieved incredible performance in generating realistic images, audio, and video data. While these models produce high-quality samples with impressive details, they often introduce unrealistic artifacts,…
Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded within model weights. However, existing LRMs often suffer from…
In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that at times, introducing hallucinations is necessary to…
Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the…