相关论文: Zero-shot Low-Field MRI Enhancement via Diffusion-…

Magnetic Resonance Imaging (MRI) is highly susceptible to motion artifacts due to the extended acquisition times required for k-space sampling. These artifacts can compromise diagnostic utility, particularly for dynamic imaging. We propose…

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator,…

Point clouds are widely used for infrastructure monitoring by providing geometric information, where segmentation is required for downstream tasks such as defect detection. Existing research has automated semantic segmentation of structural…

Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches leverage additional modalities such as language to generate…

Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while…

Magnetic resonance diffusion tensor imaging (DTI) is a critical tool for neural disease diagnosis. However, long scan time greatly hinders the widespread clinical use of DTI. To accelerate image acquisition, a feature-enhanced joint…

Diffusion models (DMs) have achieved promising performance in image restoration but haven't been explored for stereo images. The application of DM in stereo image restoration is confronted with a series of challenges. The need to…

This study introduces LRDif, a novel diffusion-based framework designed specifically for facial expression recognition (FER) within the context of under-display cameras (UDC). To address the inherent challenges posed by UDC's image…

We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, significantly…

Diffusion models (DM) have achieved remarkable promise in image super-resolution (SR). However, most of them are tailored to solving non-blind inverse problems with fixed known degradation settings, limiting their adaptability to real-world…

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention…

The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based perception is still…

While zero-shot diffusion-based compression methods have seen significant progress in recent years, they remain notoriously slow and computationally demanding. This paper presents an efficient zero-shot diffusion-based compression method…

Light fields (LFs), conducive to comprehensive scene radiance recorded across angular dimensions, find wide applications in 3D reconstruction, virtual reality, and computational photography.However, the LF acquisition is inevitably…

Imaging techniques such as functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) achieve deep, non-invasive sensing in turbid media, but they are constrained by the photon budget. Wavefront shaping (WFS) can…

The rapid adoption of HDR-capable devices has created a pressing need to convert the 8-bit Standard Dynamic Range (SDR) content into perceptually and physically accurate 10-bit High Dynamic Range (HDR). Existing inverse tone-mapping (ITM)…

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmentation, they significantly lag behind supervised models. In…

Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Anatomically consistent field-of-view (FOV) completion to recover truncated body sections has important applications in quantitative analyses of computed tomography (CT) with limited FOV. Existing solution based on conditional generative…