Related papers: MMDRFuse: Distilled Mini-Model with Dynamic Refres…
Multimodal medical image fusion plays an instrumental role in several areas of medical image processing, particularly in disease recognition and tumor detection. Traditional fusion methods tend to process each modality independently before…
Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple…
Image fusion aims to synthesize a single high-quality image from a pair of inputs captured under challenging conditions, such as differing exposure levels or focal depths. A core challenge lies in effectively handling disparities in dynamic…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks…
Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider…
Photo-realistic image restoration algorithms are typically evaluated by distortion measures (e.g., PSNR, SSIM) and by perceptual quality measures (e.g., FID, NIQE), where the desire is to attain the lowest possible distortion without…
Dataset distillation has emerged as a powerful approach for reducing data requirements in deep learning. Among various methods, distribution matching-based approaches stand out for their balance of computational efficiency and strong…
High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information…
Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models…
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion.…
In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static…
Multi-Modal Image Fusion (MMIF) aims to combine images from different modalities to produce fused images, retaining texture details and preserving significant information. Recently, some MMIF methods incorporate frequency domain information…
Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high…
Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…
Multi-modality image fusion (MMIF) in adverse weather aims to address the loss of visual information caused by weather-related degradations, providing clearer scene representations. Although less studies have attempted to incorporate…
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields…
Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…
Continual learning, the ability to acquire knowledge from new data while retaining previously learned information, is a fundamental challenge in machine learning. Various approaches, including memory replay, knowledge distillation, model…