A Neural Motion Deblurring Approach to Restore Rich Textures for Visual SLAM

机译：用于Visual SLAM还原丰富纹理的神经运动去模糊方法

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, we present a sequential video deblurring method based on a spatio-temporal recurrent network for visual SLAM. The method can be applied to any SLAM systems to make sure continuous localization even with blurred images. The quality of the deblurring method is evaluated on real-world problems: feature points extraction and SLAM, which prove the method can significantly improve the performance of tracking accuracy especially in some severe cases containing strong camera shake or fast motion.

机译：在本文中，我们提出了一种基于时空递归网络的视觉SLAM序列视频去模糊方法。该方法可以应用于任何SLAM系统，以确保即使图像模糊也可以进行连续定位。在实际问题上对去模糊方法的质量进行了评估：特征点提取和SLAM，这证明该方法可以显着提高跟踪精度的性能，特别是在某些严重的情况下，如相机抖动或运动快的情况下。

著录项

来源
《IEEE Conference on Virtual Reality and 3D User Interfaces》|2019年|996-997|共2页
会议地点
作者
Guojing Jin; Jing Chen; Jingyao Wang; Yongtian Wang;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
SLAM; Motion Blur; Deblur;

机译：SLAM;运动模糊;去模糊;

相似文献

外文文献
中文文献
专利

1. SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition [J] . Mel B Neural computation . 1997,第4期

机译：SEEMORE：在自然启发的视觉对象识别方法中结合颜色，形状和纹理直方图
2. Joint-encoding of motion and depth by visual cortical neurons: neural basis of the Pulfrich effect. [J] . Anzai A, Ohzawa I, Freeman RD Nature neuroscience . 2001,第5期

机译：视觉皮层神经元对运动和深度的联合编码：Pulfrich效应的神经基础。
3. Testing the validity of the TMS state-dependency approach: targeting functionally distinct motion-selective neural populations in visual areas V1/V2 and V5/MT+. [J] . Silvanto J, Muggleton NG NeuroImage . 2008,第4期

机译：测试TMS状态依赖方法的有效性：针对V1 / V2和V5 / MT +视觉区域中功能不同的运动选择性神经群体。
4. A Neural Motion Deblurring Approach to Restore Rich Textures for Visual SLAM [C] . Guojing Jin, Jing Chen, Jingyao Wang, IEEE Conference on Virtual Reality and 3D User Interfaces . 2019

机译：一种恢复Visual Slam的丰富纹理的神经运动脱毛方法
5. Understanding Texture Sensitivity in the Brain Visual System with Deep Neural Networks [D] . Laskar, Md Nasir Uddin. 2020

机译：了解深神经网络脑视觉系统中的纹理敏感性
6. Comparison of two elastic motion correction approaches for whole-body PET/CT: motion deblurring vs gate-to-gate motion correction [O] . Stefanie Pösse, Florian Büther, Dirk Mannweiler, 2020

机译：两种用于全身PET / CT的弹性运动校正方法的比较：运动去模糊与门到门运动校正
7. Motion deblurring in a neural network model of retino-cortical dynamics1This study was presented in part at the 1995 annual meeting of ARVO and appeared in abstract form in Investigative Ophthalmology and Visual Science 36, S52.1 [O] . Purushothaman Gopathy, Öğmen Haluk, Chen Shuai, 1998

机译：视网膜皮层动力学的神经网络模型中的运动去模糊1该研究在1995年的ARVO年会上进行了部分介绍，并以抽象形式出现在调查眼科学和视觉科学36，S52.1中
8. Singular Integrals, Image Smoothness, and the Recovery of Texture in Image Deblurring. [R] . Carasso, A. S. 2002

机译：图像去模糊中的奇异积分，图像平滑度和纹理恢复。

A Neural Motion Deblurring Approach to Restore Rich Textures for Visual SLAM

摘要

著录项

相似文献

相关主题

期刊订阅