论文阅读汇总list_综合

 
    基于计算机视觉的地面机器人深度估计及相对定位框架A Framework for Depth Estimation and Relative Localization of Ground Robots Using Computer Vision 
    2019.11.27 
   
    新的人工智能系统近乎完美的预测癫痫发作Effificient Epileptic Seizure Prediction Based on Deep Learning 
    2019.11.27 
   
    通过卷积空间传播网络进行相似性学习深度估计 Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network Code 
    2019.11.26 
   
    ActiveStereoNet:主动双目系统端到端自监督学习ActiveStereoNet: End-to-End Self-SupervisedLearning for Active Stereo Systems 
    2019.11.22 
   
    单目伪激光雷达点云3D目标检测Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud Code 
    2019.21 
   
    3D多目标追踪基准 A Baseline for 3D Multi-Object Tracking Code 
    2019.11.20 
   
    使用语义引导的雷达数据和运动双目相机的实时稠密相机重建 Real-Time Dense Depth Estimation using Semantically-Guided LIDAR Data Propagation and Motion Stereo 
    2019.11.15 
   
    虚拟法线加强深度估计几何约束 Enforcing geometric constraints of virtual normal for depth prediction Code 
    2019.11.14 
   
    MonoGRNet：一种几何推测单目三维目标定位网络MonoGRNet: A Geometric Reasoning Network for Monocular 3D ObjectLocalization Code 
    2019.11.13 
   
    攻击光流网路Attacking Optical Flow Code 
    2019.11.12 
   
    PointFlowNet:从点云中学习刚体运动表示PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds 
    2019.11.11 
   
    自动驾驶的双目视觉语义的3D物体运动跟踪Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving Code 
    2019.11.9 
   
    基于深度学习的回环检测Learning Whole-Image Descriptors for Real-time Loop Detection and Kidnap Recovery und Code 
    2019.11.6 
   
    边界像素：利用几何和形状线索进行在线多目标跟踪 Beyond Pixels: Leveraging Geometry and Shape Cues for OnlineMulti-Object Tracking Code 
    2019.11.4 
   
    半监督对抗单目深度估计Semi-Supervised Adversarial Monocular Depth Estimation 
    2019.11.3 
   
    单网络全景分割用于街道场景理解 Single Network Panoptic Segmentation for Street Scene Understanding 
    2019.10.31 
   
     Code 
    2019.10.29 
   
    三角几何学习网络：从单目到立体的三维目标检测Triangulation Learning Network: from Monocular to Stereo 3D Object Detection 
    2019.10.29 
   
    基于光流加权融合的双视单目深度估计 Two-View Monocular Depth Estimation by Optic-Flow-Weighted Fusion 2019.10.29 
     
    ROSlab：与Docker和JupyterLab交互共享ROS代码 ROSlab：Sharing ROS Code Interactively With Docker and JupyterLab Code 
    2019.10.27 
   
    Mono-Stixels：动态街景单目深度重建 Mono-Stixels: Monocular depth reconstruction of dynamic street scenes 
    2019.10.25 
   
    3D-RCNN :通过渲染对比实例级别3D目标重建 3d-rcnn: Instance-level 3d object reconstruction via renderand-compare Code 
    2019.10.24 
   
    SemanticKITTI:一个LIDAR帧语义场景理解的数据集 SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences Code 
    2019.10.23 
   
    最大期望注意力语义分割网络 Expectation-Maximization Attention Networks for Semantic Segmentation 
    2019.10.21 
   
    将物体等效为一个点 Objects as Points Code 
    2019.10.20 
   
    AutoDispNet:AutoML提高disparity估计 AutoDispNet: Improving Disparity Estimation With AutoML 
    2019.10.16 
   
    CBAM:卷积块注意力模型 CBAM: Convolutional Block Attention Module Code 
    2019.10.15 
   
    变卷积核深度图上采样 Deformable kernel networks for guided depth map upsampling Code 
    2019.10.14 
   
    用IMU监督训练连续帧之间的位姿变换的R，T的文章Learning Monocular Visual Odometrythrough Geometry-Aware Curriculum Learning 
    2019.10.13 
   
    Edgestereo:一个用于立体匹配的前后特征集成剩余金字塔网络 EdgeStereo: A Context Integrated ResidualPyramid Network for Stereo Matching 
    2019.10.8 
   
    基于EKF的摄像机内参数在线标定视觉惯性里程计可观测性分析与性能评价 
     
    相机参数在线标定Observability Analysis and Performance Evaluationof EKF-Based Visual-Inertial Odometry WithOnline Intrinsic Camera Parameter Calibration 2019.10.9 
     
    DFF-DEN：基于带细节增强网络的深度特征流手部深度视频分割 Feature Flow with Detail Enhancement Network for Hand Segmentation in Depth Video 
    2019.10.7 
   
    CBAM: Convolutional Block Attention Module 在卷积过程中加入注意力机制 Code 
    2019.10.4 
   
    单目视频的无监督尺度一致深度和自我运动学习 Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video Code 
    2019.10.3 
   
    基于注意力的上下文聚合网络用于单目视觉深度估计Attention-based Context Aggregation Network forMonocular Depth Estimation Code 
    2019.10.3 
   
    动态语义关联网络的语义回归(建立语义之间的关系) Dynamic Context Correspondence Network for Semantic Alignment Code 
    2019.9.27 
   
    DynamicFusion：非刚体场景实时重建与追踪 DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time 
    2019.9.27 
   
    深度非结构运动学习Deep Non-Rigid Structure from Motion 
    2019.9.26 
   
    基于星座的语义slam地图合并 Efficient Constellation-Based Map-Merging for Semantic SLAM 
    2019.9.24 
   
    Fusenet：通过基于融合的cnn架构将深度融入语义分割 FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture Code 
    2019.9.22 
   
    orbslam-Atlas：一个鲁邦而精确的多地图系统ORBSLAM-Atlas: a robust and accurate multi-map system 
    2019.9.21 
   
    非直接双目匹配的多光谱视觉里程计 Multi-Spectral Visual Odometry without Explicit Stereo Matching 
    2019.9.20 
   
    基于卷积神经网络航空影像的电力线绝缘子缺陷检测 Detection of Power Line Insulator DefectsUsing Aerial Images Analyzed WithConvolutional Neural Networks 
    2019.9.19 
   
    TensorMask:稠密目标分割基础 TensorMask: A Foundation for Dense Object Segmentation Code 
    2019.9.18 
   
    Gated2Depth：实时门控图像得到稠密雷达深度图 Gated2Depth: Real-time Dense Lidar from Gated Images Code 
    2019.9.17 
   
    3D-RelNet:预测场景中所有对象的三维姿势和形状 3D-RelNet: Joint Object and Relational Network for 3D Prediction Code 
    2019.9.16 
   
    单目3D联合车辆识别和检测 Joint Monocular 3D Vehicle Detection and Tracking Code 
    2019.9.15 
   
    基于rgbd感知的增量式种类发现语义分割Incremental Class Discovery for Semantic Segmentation with RGBD Sensing 
    2019.9.14 
   
    实时video深度估计的时间关联研究 Exploiting temporal consistency for real-time video depth estimation Code 
    2019.9.13 
   
    ADCrowNet:用于人群理解的注意力嵌入可变形卷积网络 ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding Code 
    2019.9.9 
   
    单目SLAM半稠密3D语义地图 Semi-Dense 3D Semantic Mapping from Monocular SLAM 
    2019.9.8 
   
    Aggregation of Rich Depth-Aware Features in a　Modified Stacked Generalization Model　for Single Image Depth Estimation 
    2019.9.7 
   
    DADA：语义分割中的深度感知域自适应 DADA: Depth-Aware Domain Adaptation in Semantic Segmentation Code 
    2019.9.7 
   
    ORBSLAM-Atlas:一个鲁棒准确的多地图系统 ORBSLAM-Atlas: a robust and accurate multi-map system 
    2019.9.6 
   
    EDVR:基于变卷积神经网络的视频重建 EDVR:Video Restoration with Enhanced Deformable Convolutional Networks Code 
    2019.9.4 
   
    Deformable ConvNets v2 Deformable ConvNets v2: More Deformable, Better Results Code 
    2019.9.3 
   
    基于递归神经网络的非完整移动机器人自适应跟踪控制[Adaptive Tracking Control of Nonholonomic Mobile Manipulators Using 
     
    Recurrent Neural Networks](https://link.springer.com/article/10.1007%2Fs12555-017-0309-6) 
    2019.9.2 
   
    DA-RNN:基于数据关联网络的语义建图 DA-RNN: Semantic Mapping with Data AssociatedRecurrent Neural Code 
    2019.9.1 
   
    Fusenet：通过基于融合CNN架构将深度融入语义分割 FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture 
    2019.8.30 
   
    深度，法线，3D-2D图像，3D语义分割数据集 结合2D-3D室内语义场景理解数据集 Joint 2D-3D-Semantic Data for Indoor Scene Understanding Code 
    2019.8.29 
   
    自注意蒸馏法学习轻型车道检测Learning Lightweight Lane Detection CNNs by Self Attention Distillation Code 
    2019.8.28 
   
    强记忆力 E3D-LSTM 网络 _ 李飞飞 EIDETIC 3D LSTM: A MODEL FOR VIDEO PREDICTION AND BEYOND 
    2019.8.27 
   
    大规模高效三维环境自主探索 Effificient Autonomous Exploration Planning of Large Scale 3D-Environments 
    2019.8.26 
   
    多尺度注意力网络：尺度意识的语义分割 [Attention to Scale: Scale-aware Semantic Image Segmentation 
     
    ](http://liangchiehchen.com/projects/DeepLab.html) Code 
    2019.8.25 
   
    MobileNetV2 MobileNetV2: Inverted Residuals and Linear Code 
    2019.8.24 
   
    DeepLab_V3 Rethinking Atrous Convolution for Semantic Image Segmentation Code 
    2019.8.23 
   
    RGB-D语义分割 综述RGB-D SEMANTIC SEGMENTATION: A REVIEW 
    [2019.8.21(https://articles.zsxq.com/id_cwqs54712tqd.html) 
   
    基于深度注意力分类网络的鲁棒深度估计Deep attention-based classification network for robust depth prediction Code 
    2019.8.19 
   
    Displets Displets: Resolving Stereo Ambiguities using Object Knowledge Code 
    2019.8.18 
   
    深度感知下的目标实例分割 deep-aware object instance segmentation  
    2019.8.16 
   
     Depth-aware CNN for RGB-D Segmentation Code 
    2019.8.15 
   
     Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation  
    2019.8.1 
   
    Dispsegnet：利用语义从立体图像端到端学习视差估计 DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery  
    2019.8.1 
   
     [Code] 
    2019.8.14

基于计算机视觉的地面机器人深度估计及相对定位框架A Framework for Depth Estimation and Relative Localization of Ground Robots Using Computer Vision	2019.11.27
新的人工智能系统近乎完美的预测癫痫发作Effificient Epileptic Seizure Prediction Based on Deep Learning	2019.11.27
通过卷积空间传播网络进行相似性学习深度估计 Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network Code	2019.11.26
ActiveStereoNet:主动双目系统端到端自监督学习ActiveStereoNet: End-to-End Self-SupervisedLearning for Active Stereo Systems	2019.11.22
单目伪激光雷达点云3D目标检测Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud Code	2019.21
3D多目标追踪基准 A Baseline for 3D Multi-Object Tracking Code	2019.11.20
使用语义引导的雷达数据和运动双目相机的实时稠密相机重建 Real-Time Dense Depth Estimation using Semantically-Guided LIDAR Data Propagation and Motion Stereo	2019.11.15
虚拟法线加强深度估计几何约束 Enforcing geometric constraints of virtual normal for depth prediction Code	2019.11.14
MonoGRNet：一种几何推测单目三维目标定位网络MonoGRNet: A Geometric Reasoning Network for Monocular 3D ObjectLocalization Code	2019.11.13
攻击光流网路Attacking Optical Flow Code	2019.11.12
PointFlowNet:从点云中学习刚体运动表示PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds	2019.11.11
自动驾驶的双目视觉语义的3D物体运动跟踪Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving Code	2019.11.9
基于深度学习的回环检测Learning Whole-Image Descriptors for Real-time Loop Detection and Kidnap Recovery und Code	2019.11.6
边界像素：利用几何和形状线索进行在线多目标跟踪 Beyond Pixels: Leveraging Geometry and Shape Cues for OnlineMulti-Object Tracking Code	2019.11.4
半监督对抗单目深度估计Semi-Supervised Adversarial Monocular Depth Estimation	2019.11.3
单网络全景分割用于街道场景理解 Single Network Panoptic Segmentation for Street Scene Understanding	2019.10.31
Code	2019.10.29
三角几何学习网络：从单目到立体的三维目标检测Triangulation Learning Network: from Monocular to Stereo 3D Object Detection	2019.10.29
基于光流加权融合的双视单目深度估计 Two-View Monocular Depth Estimation by Optic-Flow-Weighted Fusion 2019.10.29
ROSlab：与Docker和JupyterLab交互共享ROS代码 ROSlab：Sharing ROS Code Interactively With Docker and JupyterLab Code	2019.10.27
Mono-Stixels：动态街景单目深度重建 Mono-Stixels: Monocular depth reconstruction of dynamic street scenes	2019.10.25
3D-RCNN :通过渲染对比实例级别3D目标重建 3d-rcnn: Instance-level 3d object reconstruction via renderand-compare Code	2019.10.24
SemanticKITTI:一个LIDAR帧语义场景理解的数据集 SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences Code	2019.10.23
最大期望注意力语义分割网络 Expectation-Maximization Attention Networks for Semantic Segmentation	2019.10.21
将物体等效为一个点 Objects as Points Code	2019.10.20
AutoDispNet:AutoML提高disparity估计 AutoDispNet: Improving Disparity Estimation With AutoML	2019.10.16
CBAM:卷积块注意力模型 CBAM: Convolutional Block Attention Module Code	2019.10.15
变卷积核深度图上采样 Deformable kernel networks for guided depth map upsampling Code	2019.10.14
用IMU监督训练连续帧之间的位姿变换的R，T的文章Learning Monocular Visual Odometrythrough Geometry-Aware Curriculum Learning	2019.10.13
Edgestereo:一个用于立体匹配的前后特征集成剩余金字塔网络 EdgeStereo: A Context Integrated ResidualPyramid Network for Stereo Matching	2019.10.8
基于EKF的摄像机内参数在线标定视觉惯性里程计可观测性分析与性能评价
相机参数在线标定Observability Analysis and Performance Evaluationof EKF-Based Visual-Inertial Odometry WithOnline Intrinsic Camera Parameter Calibration 2019.10.9
DFF-DEN：基于带细节增强网络的深度特征流手部深度视频分割 Feature Flow with Detail Enhancement Network for Hand Segmentation in Depth Video	2019.10.7
CBAM: Convolutional Block Attention Module 在卷积过程中加入注意力机制 Code	2019.10.4
单目视频的无监督尺度一致深度和自我运动学习 Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video Code	2019.10.3
基于注意力的上下文聚合网络用于单目视觉深度估计Attention-based Context Aggregation Network forMonocular Depth Estimation Code	2019.10.3
动态语义关联网络的语义回归(建立语义之间的关系) Dynamic Context Correspondence Network for Semantic Alignment Code	2019.9.27
DynamicFusion：非刚体场景实时重建与追踪 DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time	2019.9.27
深度非结构运动学习Deep Non-Rigid Structure from Motion	2019.9.26
基于星座的语义slam地图合并 Efficient Constellation-Based Map-Merging for Semantic SLAM	2019.9.24
Fusenet：通过基于融合的cnn架构将深度融入语义分割 FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture Code	2019.9.22
orbslam-Atlas：一个鲁邦而精确的多地图系统ORBSLAM-Atlas: a robust and accurate multi-map system	2019.9.21
非直接双目匹配的多光谱视觉里程计 Multi-Spectral Visual Odometry without Explicit Stereo Matching	2019.9.20
基于卷积神经网络航空影像的电力线绝缘子缺陷检测 Detection of Power Line Insulator DefectsUsing Aerial Images Analyzed WithConvolutional Neural Networks	2019.9.19
TensorMask:稠密目标分割基础 TensorMask: A Foundation for Dense Object Segmentation Code	2019.9.18
Gated2Depth：实时门控图像得到稠密雷达深度图 Gated2Depth: Real-time Dense Lidar from Gated Images Code	2019.9.17
3D-RelNet:预测场景中所有对象的三维姿势和形状 3D-RelNet: Joint Object and Relational Network for 3D Prediction Code	2019.9.16
单目3D联合车辆识别和检测 Joint Monocular 3D Vehicle Detection and Tracking Code	2019.9.15
基于rgbd感知的增量式种类发现语义分割Incremental Class Discovery for Semantic Segmentation with RGBD Sensing	2019.9.14
实时video深度估计的时间关联研究 Exploiting temporal consistency for real-time video depth estimation Code	2019.9.13
ADCrowNet:用于人群理解的注意力嵌入可变形卷积网络 ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding Code	2019.9.9
单目SLAM半稠密3D语义地图 Semi-Dense 3D Semantic Mapping from Monocular SLAM	2019.9.8
Aggregation of Rich Depth-Aware Features in a　Modified Stacked Generalization Model　for Single Image Depth Estimation	2019.9.7
DADA：语义分割中的深度感知域自适应 DADA: Depth-Aware Domain Adaptation in Semantic Segmentation Code	2019.9.7
ORBSLAM-Atlas:一个鲁棒准确的多地图系统 ORBSLAM-Atlas: a robust and accurate multi-map system	2019.9.6
EDVR:基于变卷积神经网络的视频重建 EDVR:Video Restoration with Enhanced Deformable Convolutional Networks Code	2019.9.4
Deformable ConvNets v2 Deformable ConvNets v2: More Deformable, Better Results Code	2019.9.3
基于递归神经网络的非完整移动机器人自适应跟踪控制[Adaptive Tracking Control of Nonholonomic Mobile Manipulators Using
Recurrent Neural Networks](https://link.springer.com/article/10.1007%2Fs12555-017-0309-6)	2019.9.2
DA-RNN:基于数据关联网络的语义建图 DA-RNN: Semantic Mapping with Data AssociatedRecurrent Neural Code	2019.9.1
Fusenet：通过基于融合CNN架构将深度融入语义分割 FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture	2019.8.30
深度，法线，3D-2D图像，3D语义分割数据集结合2D-3D室内语义场景理解数据集 Joint 2D-3D-Semantic Data for Indoor Scene Understanding Code	2019.8.29
自注意蒸馏法学习轻型车道检测Learning Lightweight Lane Detection CNNs by Self Attention Distillation Code	2019.8.28
强记忆力 E3D-LSTM 网络 _ 李飞飞 EIDETIC 3D LSTM: A MODEL FOR VIDEO PREDICTION AND BEYOND	2019.8.27
大规模高效三维环境自主探索 Effificient Autonomous Exploration Planning of Large Scale 3D-Environments	2019.8.26
多尺度注意力网络：尺度意识的语义分割 [Attention to Scale: Scale-aware Semantic Image Segmentation
](http://liangchiehchen.com/projects/DeepLab.html) Code	2019.8.25
MobileNetV2 MobileNetV2: Inverted Residuals and Linear Code	2019.8.24
DeepLab_V3 Rethinking Atrous Convolution for Semantic Image Segmentation Code	2019.8.23
RGB-D语义分割综述RGB-D SEMANTIC SEGMENTATION: A REVIEW	[2019.8.21(https://articles.zsxq.com/id_cwqs54712tqd.html)
基于深度注意力分类网络的鲁棒深度估计Deep attention-based classification network for robust depth prediction Code	2019.8.19
Displets Displets: Resolving Stereo Ambiguities using Object Knowledge Code	2019.8.18
深度感知下的目标实例分割 deep-aware object instance segmentation	2019.8.16
Depth-aware CNN for RGB-D Segmentation Code	2019.8.15
Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation	2019.8.1
Dispsegnet：利用语义从立体图像端到端学习视差估计 DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery	2019.8.1
[Code]	2019.8.14