Degradation-resistant unfolding network for heterogeneous image fusion
Heterogeneous image fusion (HIF) techniques aim to enhance image quality by merging
complementary information from images captured by different sensors. Among these …
complementary information from images captured by different sensors. Among these …
Strategic preys make acute predators: Enhancing camouflaged object detectors by generating camouflaged objects
Camouflaged object detection (COD) is the challenging task of identifying camouflaged
objects visually blended into surroundings. Albeit achieving remarkable success, existing …
objects visually blended into surroundings. Albeit achieving remarkable success, existing …
Hqg-net: Unpaired medical image enhancement with high-quality guidance
Unpaired medical image enhancement (UMIE) aims to transform a low-quality (LQ) medical
image into a high-quality (HQ) one without relying on paired images for training. While most …
image into a high-quality (HQ) one without relying on paired images for training. While most …
Unihead: unifying multi-perception for detection heads
The detection head constitutes a pivotal component within object detectors, tasked with
executing both classification and localization functions. Regrettably, the commonly used …
executing both classification and localization functions. Regrettably, the commonly used …
A lightweight pixel-level unified image fusion network
In recent years, deep-learning-based pixel-level unified image fusion methods have
received more and more attention due to their practicality and robustness. However, they …
received more and more attention due to their practicality and robustness. However, they …
Reti-diff: Illumination degradation image restoration with retinex-based latent diffusion model
Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of
degraded images and mitigate the adverse effects of deteriorated illumination. Among these …
degraded images and mitigate the adverse effects of deteriorated illumination. Among these …
[HTML][HTML] TDFusion: When tensor decomposition meets medical image fusion in the nonsubsampled shearlet transform domain
R Zhang, Z Wang, H Sun, L Deng, H Zhu - Sensors, 2023 - mdpi.com
In this paper, a unified optimization model for medical image fusion based on tensor
decomposition and the non-subsampled shearlet transform (NSST) is proposed. The model …
decomposition and the non-subsampled shearlet transform (NSST) is proposed. The model …
STFuse: Infrared and Visible Image Fusion via Semisupervised Transfer Learning
X Wang, Z Guan, W Qian, J Cao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Infrared and visible image fusion (IVIF) aims to obtain an image that contains
complementary information about the source images. However, it is challenging to define …
complementary information about the source images. However, it is challenging to define …
Concealed object segmentation with hierarchical coherence modeling
Concealed object segmentation (COS) is a challenging task that involves localizing and
segmenting those concealed objects that are visually blended with their surrounding …
segmenting those concealed objects that are visually blended with their surrounding …
DI-MVS: Learning Efficient Multi-View Stereo With Depth-Aware Iterations
Learning-based Multi-View Stereo (MVS) methods aim to reconstruct 3D scenes from a set
of 2D calibrated images. However, existing learning-based MVS methods often overlook …
of 2D calibrated images. However, existing learning-based MVS methods often overlook …