Shanquan Ying,Jianfeng Zhao,Guannan Li et al.
Shanquan Ying et al.
Image matching is a fundamental problem in computer vision, serving as a core component in tasks such as visual localization, structure from motion, and SLAM. While recent advances using convolutional neural networks and transformer have ac...
Improved Face Image Super-Resolution Model Based on Generative Adversarial Network [0.03%]
基于生成对抗网络的改进人脸超分辨率模型
Qingyu Liu,Yeguo Sun,Lei Chen et al.
Qingyu Liu et al.
Image super-resolution (SR) models based on the generative adversarial network (GAN) face challenges such as unnatural facial detail restoration and local blurring. This paper proposes an improved GAN-based model to address these issues. Fi...
A Lightweight Semantic Segmentation Model for Underwater Images Based on DeepLabv3 [0.03%]
基于DeepLabv3的 underwater图像语义分割轻量级模型
Chongjing Xiao,Zhiyu Zhou,Yanjun Hu
Chongjing Xiao
Underwater object image processing is a crucial technology for marine environmental exploration. The complexity of marine environments typically results in underwater object images exhibiting color deviation, imbalanced contrast, and blurri...
From Physically Based to Generative Models: A Survey on Underwater Image Synthesis Techniques [0.03%]
基于物理与生成模型的水下图像合成方法综述
Lucas Amparo Barbosa,Antonio Lopes Apolinario Jr
Lucas Amparo Barbosa
The underwater world has gained significant attention in research in recent years, particularly in the context of ocean exploration. Images serve as a valuable data source for underwater tasks, but they face several issues related to light ...
Noise Suppressed Image Reconstruction for Quanta Image Sensors Based on Transformer Neural Networks [0.03%]
基于变压器神经网络的量子图像传感器噪声抑制图像重建方法
Guanjie Wang,Zhiyuan Gao
Guanjie Wang
The photon detection capability of quanta image sensors make them an optimal choice for low-light imaging. To address Possion noise in QIS reconstruction caused by spatio-temporal oversampling characteristic, a deep learning-based noise sup...
A Transfer Learning-Based VGG-16 Model for COD Detection in UV-Vis Spectroscopy [0.03%]
一种基于迁移学习的VGG-16网络模型用于UV-Vis光谱学COD检测中
Jingwei Li,Iqbal Muhammad Tauqeer,Zhiyu Shao et al.
Jingwei Li et al.
Chemical oxygen demand (COD) serves as a key indicator of organic pollution in water bodies, and its rapid and accurate detection is crucial for environmental protection. Recently, ultraviolet-visible (UV-Vis) spectroscopy has gained popula...
Junjie Wei,Ying Song
Junjie Wei
The real-time rendering of large-scale curve-based surfaces (e.g., hair, fabrics) requires efficient handling of bidirectional curve-scattering distribution functions (BCSDFs). While curve-based material models are essential for capturing a...
AI-Driven Automated Blood Cell Anomaly Detection: Enhancing Diagnostics and Telehealth in Hematology [0.03%]
基于人工智能的自动化血液细胞异常检测：增强血液学诊断和远程医疗
Sami Naouali,Oussama El Othmani
Sami Naouali
Hematology plays a critical role in diagnosing and managing a wide range of blood-related disorders. The manual interpretation of blood smear images, however, is time-consuming and highly dependent on expert availability. Moreover, it is pa...
Unleashing the Potential of Residual and Dual-Stream Transformers for the Remote Sensing Image Analysis [0.03%]
解锁残差和双流变压器在遥感图像分析中的潜力
Priya Mittal,Vishesh Tanwar,Bhisham Sharma et al.
Priya Mittal et al.
The categorization of remote sensing satellite imagery is crucial for various applications, including environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) hav...
Beyond Handcrafted Features: A Deep Learning Framework for Optical Flow and SLAM [0.03%]
超越手工制作的特征：一个用于光流和即时定位与地图构建的深度学习框架
Kamran Kazi,Arbab Nighat Kalhoro,Farida Memon et al.
Kamran Kazi et al.
This paper presents a novel approach for visual Simultaneous Localization and Mapping (SLAM) using Convolution Neural Networks (CNNs) for robust map creation. Traditional SLAM methods rely on handcrafted features, which are susceptible to v...