首页/论文/2006.03182

arXiv 2006.031822020-06-05cs.CV

MSDU-net: A Multi-Scale Dilated U-net for Blur Detection

Xidian University（西安电子科技大学）

Fan Yang, Xiao Xiao

英文摘要：

Blur detection is the separation of blurred and clear regions of an image, which is an important and challenging task in computer vision. In this work, we regard blur detection as an image segmentation problem. Inspired by the success of the U-net architecture for image segmentation, we design a Multi-Scale Dilated convolutional neural network based on U-net, which we call MSDU-net. The MSDU-net uses a group of multi-scale feature extractors with dilated convolutions to extract texture information at different scales. The U-shape architecture of the MSDU-net fuses the different-scale texture features and generates a semantic feature which allows us to achieve better results on the blur detection task. We show that using the MSDU-net we are able to outperform other state of the art blur detection methods on two publicly available benchmarks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

Texas A&M University（得克萨斯农工大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

This paper studies the challenging problem of fingerprint image denoising and inpainting. To tackle the challenge of suppressing complicated artifacts (blur, brightness, contrast, elastic transformation, occlusion, scratch, resolution, rotation, and so on) while preserving fine textures, we develop a multi-scale convolutional network, termed U- Finger. Based on the domain expertise, we show that the usage of dilated convolutions as well as the removal of padding have important positive impacts on the final restoration performance, in addition to multi-scale cascaded feature modules. Our model …

2018-08-05cs.CV

BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring

National Tsing Hua University（国立清华大学）；National Chengchi University（国立政治大学）；Qualcomm Technologies, Inc.（高通技术公司）；National Yang Ming Chiao Tung University（国立阳明交通大学）

Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform. Previous research attempted to solve non-uniform blurs using self-recurrent multiscale, multi-patch, or multi-temporal architectures with self-attention to obtain decent results. However, using self-recurrent frameworks typically lead to a longer inference time, while inter-pixel or inter-channel self-attention may cause excessive memory usage. This paper proposes a Blur-aware Attention Network (BANet), that accomplishes accurate and efficient deb…

2022-10-25cs.CV

面向越野分割的地形增强分辨率感知细化注意力机制

Terrain-Enhanced Resolution-aware Refinement Attention for Off-Road Segmentation

Gachon University（嘉泉大学）

提出一种分辨率感知token解码器，通过低分辨率瓶颈、门控交叉注意力与类别感知点细化，结合边界带一致性正则化，在噪声标签下平衡全局语义、局部一致性与边界保真度，实现越野语义分割的竞争性能与稳定性提升。

2025-11-03cs.CV

Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction

George Mason University（乔治梅森大学）；The MITRE Corporation（MITRE公司）

In photoacoustic tomography (PAT), the acoustic pressure waves produced by optical excitation are measured by an array of detectors and used to reconstruct an image. Sparse spatial sampling and limited-view detection are two common challenges faced in PAT. Reconstructing from incomplete data using standard methods results in severe streaking artifacts and blurring. We propose a modified convolutional neural network (CNN) architecture termed Dense Dilation UNet (DD-UNet) for correcting artifacts in 3D PAT. The DD-Net leverages the benefits of dense connectivity and dilated convolutions to impro…

2021-04-07cs.CVcs.LGeess.IV

CSSegNet: Fine-Grained Cardiac Structures Segmentation Using Dilated Pyramid Pooling in U-net

University of Michigan – Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University（上海交通大学密歇根学院）

Cardiac structure segmentation plays an important role in medical analysis procedures. Images' blurred boundaries issue always limits the segmentation performance. To address this difficult problem, we presented a novel network structure which embedded dilated pyramid pooling block in the skip connections between networks' encoding and decoding stage. A dilated pyramid pooling block is made up of convolutions and pooling operations with different vision scopes. Equipped the model with such module, it could be endowed with multi-scales vision ability. Together combining with other techniques, i…

2019-07-02cs.CVstat.AP

用于事件相机目标检测的循环视觉Transformer

Recurrent Vision Transformers for Object Detection with Event Cameras

University of Zurich（苏黎世大学）

本文提出循环视觉Transformer（RVTs），通过卷积先验、局部与扩张全局自注意力及循环时序聚合的多阶段设计，在保持事件相机目标检测精度的同时将推理时间降低6倍，并在Gen1数据集上以更少参数实现47.2% mAP和小于12毫秒的快速推理。

2023-05-25cs.CV

更多相关论文收起更多论文

SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring

Fujian Normal University（福建师范大学）；JOYY AI GROUP（欢聚集团AI团队）；China Design Group Co Ltd（中设集团有限公司）

Image deblurring is a classical computer vision problem that aims to recover a sharp image from a blurred image. To solve this problem, existing methods apply the Encode-Decode architecture to design the complex networks to make a good performance. However, most of these methods use repeated up-sampling and down-sampling structures to expand the receptive field, which results in texture information loss during the sampling process and some of them design the multiple stages that lead to difficulties with convergence. Therefore, our model uses dilated convolution to enable the obtainment of the…

2021-10-12cs.CVeess.IV

DeepPyramid+：使用金字塔视图融合与可变形金字塔感受野的医学图像分割

DeepPyramid+: Medical Image Segmentation using Pyramid View Fusion and Deformable Pyramid Reception

University of Bern（伯尔尼大学）；Inselspital（Inselspital医院（伯尔尼大学医院））；University of Klagenfurt（克拉根福大学）

本文提出 DeepPyramid+ 医学图像分割网络，通过 PVF 与 DPR 模块增强多尺度、可变形特征提取，在多模态数据集上显著提升域内与跨域分割性能。

2023-12-06cs.CV

AD-Net：基于注意力的扩张卷积残差网络与引导解码器，用于鲁棒的皮肤病变分割

AD-Net: Attention-based dilated convolutional residual network with guided decoder for robust skin lesion segmentation

COMSATS University Islamabad (CUI)（COMSATS大学伊斯兰堡校区）；University of Engineering and Technology (UET) Lahore（拉合尔工程技术大学）；University of New South Wales（新南威尔士大学）；IBADAT International University Islamabad（伊巴达特国际大学伊斯兰堡校区）

针对皮肤病变边界模糊和外观差异导致的分割难题，提出结合 ASFEB 与引导解码器的轻量扩张卷积残差网络 AD-Net，并在四个基准上验证其优于前沿方法。

2024-09-09cs.AIcs.CV

Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy

University of Oxford（牛津大学）；Oxford University Hospitals NHS Trust（牛津大学医院NHS信托基金会）

Kidney stones represent a considerable burden for public health-care systems. Ureteroscopy with laser lithotripsy has evolved as the most commonly used technique for the treatment of kidney stones. Automated segmentation of kidney stones and laser fiber is an important initial step to performing any automated quantitative analysis of the stones, particularly stone-size estimation, that helps the surgeon decide if the stone requires more fragmentation. Factors such as turbid fluid inside the cavity, specularities, motion blur due to kidney movements and camera motion, bleeding, and stone debris…

2021-04-02cs.CVeess.IV

SPEEDNet：用于结肠镜图像的显著金字塔增强编码器-解码器网络

SPEEDNet: Salient Pyramidal Enhancement Encoder-Decoder Network for Colonoscopy Images

Indian Institute of Information Technology (IIIT) Jabalpur（印度贾巴尔普尔信息技术学院）；Gujarat Technological University（古吉拉特理工大学）；Indian Institute of Technology (IIT) Roorkee（印度理工学院鲁尔基分校）；SVIMS Tirupati（蒂鲁帕蒂斯里文卡特斯瓦拉医学科学研究所）

SPEEDNet提出DIPC金字塔卷积融合模块，在结肠镜图像病变分割中以9.81 MB小模型取得0.952 Dice和0.971召回率，优于UNet等网络。

2023-12-02cs.CVcs.LGeess.IV

基于注意力引导网络的单图像细节保持深度估计

Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks

Beihang University（北京航空航天大学）；Advanced Digital Sciences Center（先进数字科学中心）；Data61-CSIRO（联邦科学与工业研究组织Data61）；Australian National University（澳大利亚国立大学）

提出一种结合密集特征提取器与注意力融合的深度估计网络，实现快速且细节保持的单图像深度预测。

2018-09-03cs.CV

Image Fine-grained Inpainting

Xidian University（西安电子科技大学）

Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To mitigate this problem, in this paper, we present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. Benefited from the property of this network, we can more easily recover large regions in an incomplete image. To better train this efficient generator, except for frequently-used VGG …

2020-10-04cs.CVcs.MM

面向息肉分割的边缘感知特征聚合网络

Edge-aware Feature Aggregation Network for Polyp Segmentation

Nanjing University of Science and Technology（南京理工大学）；NPU（西北工业大学）；Southeast University（东南大学）；ETH Zürich（苏黎世联邦理工学院）

本文提出边缘感知特征聚合网络EFA-Net，通过边缘引导、尺度感知卷积和跨层级融合模块解决息肉分割中的尺度变化与边界模糊问题，在多个结肠镜数据集上取得优于现有方法的性能。

2025-02-05cs.CV