这里找的是关于室内定位或建图以及深度学习结合的文章,而且基本是使用视觉信息的。有些是已经发表了的,会议及时间写在名字后面了,其余的则是没有发表但是在arXiv上发布了的。
-
Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network IROS2019
-
Localization of Unmanned Aerial Vehicles in Corridor Environments using Deep Learning
-
Learning to Reconstruct and Understand Indoor Scenes from Sparse Views
-
Indoor GeoNet: Weakly Supervised Hybrid Learning for Depth and Pose Estimation
这里是关于SLAM与深度学习结合的比较经典的文章
-
VSO: Visual Semantic Odometry ECCV 2018
-
Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving ECCV 2018
-
Long-term Visual Localization using Semantically Segmented Images ICRA 2018
-
DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes IROS 2018
-
DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments IROS 2018
-
SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks ICRA 2017
-
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects ISMAR 2018
- Revealing Scenes by Inverting Structure from Motion Reconstructions
- Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
- What Do Single-view 3D Reconstruction Networks Learn?
- Learning View Priors for Single-view 3D Reconstruction
- Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation
- Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
- Understanding the Limitations of CNN-based Absolute Camera Pose Regression
- DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
- Segmentation-driven 6D Object Pose Estimation
- PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds
- From Coarse to Fine: Robust Hierarchical Localization at Large Scale
这里摘录的是ICRA 2019的文章列表中看上去内容相近或者比较感兴趣的文章名称
- Autonomous Exploration, Reconstruction, and Surveillance of 3D Environments Aided by Deep Learning
- Sparse2Dense - From Direct Sparse Odometry to Dense 3D Reconstruction
- A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM
- Hierarchical Depthwise Graph Convolutional Neural Network for 3D Semantic Segmentation of Point Clouds
- Robust 3D Object Classification by Combining Point Pair Features and Graph Convolution
- A Fast and Robust 3D Person Detector and Posture Estimator for Mobile Robotic Applications
- ScalableFusion - High-Resolution Mesh-Based Real-Time 3D Reconstruction
- Dense 3D Visual Mapping Via Semantic Simplification
- 2D3D-MatchNet - Learning to Match Keypoints across 2D Image and 3D Point Cloud
- Prediction Maps for Real-Time 3D Footstep Planning in Dynamic Environments
- DeepFusion - Real-Time Dense 3D Reconstruction for Monocular SLAM Using Single-View Depth and Gradient Predictions
- MVX-Net - Multimodal VoxelNet for 3D Object Detection
- Sparse2Dense - From Direct Sparse Odometry to Dense 3D Reconstruction
- On-Line 3D Active Pose-Graph SLAM Based on Key Poses Using Graph Topology and Sub-Maps
- Tightly-Coupled Visual-Inertial Localization and 3D Rigid-Body Target Tracking