Related papers: Edge-preserving Image Denoising via Multi-scale Ad…
Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different…
Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve…
The advancement of multi-object tracking (MOT) technologies presents the dual challenge of maintaining high performance while addressing critical security and privacy concerns. In applications such as pedestrian tracking, where sensitive…
Recent advancements in edge computing have significantly enhanced the AI capabilities of Internet of Things (IoT) devices. However, these advancements introduce new challenges in knowledge exchange and resource management, particularly…
Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i.i.d. Gaussian noise. We aim to obviate this unrealistic setting by developing a methodology for benchmarking…
Microstructure imaging is crucial in materials science, but experimental images often introduce noise that obscures critical structural details. This study presents a novel deep learning approach for robust microstructure image denoising,…
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features…
Real-time image denoising is essential for modern mobile photography but remains challenging due to the strict latency and power constraints of edge devices. This paper presents FastSHADE (Fast Self-augmented Hierarchical Asymmetric…
Whole-slide images (WSIs) contain tissue information distributed across multiple magnification levels, yet most self-supervised methods treat these scales as independent views. This separation prevents models from learning representations…
Decentralized stochastic optimization has emerged as a fundamental paradigm for large-scale machine learning. However, practical implementations often rely on biased gradient estimators arising from communication compression or inexact…
We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the…
Existing edge-aware camouflaged object detection (COD) methods normally output the edge prediction in the early stage. However, edges are important and fundamental factors in the following segmentation task. Due to the high visual…
Detecting small targets in drone imagery is challenging due to low resolution, complex backgrounds, and dynamic scenes. We propose EDNet, a novel edge-target detection framework built on an enhanced YOLOv10 architecture, optimized for…
Edge intelligence requires to fast access distributed data samples generated by edge devices. The challenge is using limited radio resource to acquire massive data samples for training machine learning models at edge server. In this…
As the rapid growth of high-speed and deep-tissue imaging in biomedical research, it is urgent to find a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional…
In Optical Coherence Tomography (OCT), speckle noise significantly hampers image quality, affecting diagnostic accuracy. Current methods, including traditional filtering and deep learning techniques, have limitations in noise reduction and…
In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data…
Identifying unknown differential equations from a given set of discrete time dependent data is a challenging problem. A small amount of noise can make the recovery unstable, and nonlinearity and differential equations with varying…
Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks. When dealing with photos captured under non-uniform illumination, existing…
Patient scans from MRI often suffer from noise, which hampers the diagnostic capability of such images. As a method to mitigate such artifact, denoising is largely studied both within the medical imaging community and beyond the community…