一、關注的論文類別
- SLAM & VO & Tracking
- 機器智能系統性能優化
- 語義
- 傳感器相關
- 地圖和重建
- 數據集相關
- 機器智能系統的嶄新研究
- 數學計算技術
- 人機協作 & 多機協作
- 移動機器人 & 無人車
二、論文關鍵信息
0. SLAM & VO & Tracking
| 論文關鍵信息 | 論文題目 |
|---|---|
| VINS綜述 | A review of vio from filtering and optimisation perspectives |
| Rolling Shutter，李明揚 | Real-time Motion Tracking on a Cellphone using Inertial Sensing and a Rolling-Shutter Camera |
| Rolling Shutter | Monocular Visual Odometry with a Rolling Shutter Camera |
| 點線VO，ICRA2017，應對低紋理、光照變化和快速移動；跟蹤部分維持關鍵幀深度圖，光度誤差+邊緣幾何誤差 | Direct Monocular Odometry Using Points and Lines |
| 點線SLAM，應對低紋理（城市，室內），基於ORBSLAM | PL-SLAM: Real-Time Monocular Visual SLAM with Points and Lines |
| 只關注興趣區域的DSO，場景解析輔助特徵選取 | SalientDSO: Bringing Attention to Direct Sparse Odometry |
| 拓撲SLAM，Voronoi圖 | Topological Simultaneous Localization and Mapping (SLAM): Toward Exact Localization Without Explicit Localization |
| Cloud Based Localization | Global Localization from Monocular SLAM on a Mobile Phone |
| 醫療SLAM | Markerless Inside-Out Tracking for Interventional Applications |
| DVS，事件相機，1MHz，無結構測量模型 | Event-Based Visual Inertial Odometry |
| 結合語義，適用平面低紋理場景，Shichao Yang, Michael Kaess | Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments |
| 關鍵點跟蹤，考慮形變和光照，Stefano Soatto | Real-time feature tracking and outlier rejection with changes in illumination |
| 區域跟蹤，考慮形變和光照，改進的SSD | Real-Time Tracking of Image Regions with Changes in Geometry and Illumination |
| 平面物體跟蹤，考慮光照，利用梯度朝向信息 | Illumination Insensitive Efficient Second-order Minimization for Planar Object Tracking |
1. 機器智能系統性能優化
| 論文關鍵信息 | 論文題目 |
|---|---|
| 網絡壓縮 | LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems |
| 提高圖像分類精度 | Dilated Residual Networks |
| 神經網絡效率精度優化 | Model Complexity-Accuracy Trade-off for a Convolutional Neural Network |
2. 語義
| 論文關鍵信息 | 論文題目 |
|---|---|
| 快速語義三維重建 | Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation |
| 語義視覺定位，描述子學習，Andreas Geiger | Semantic Visual Localization |
| 語義SLAM，目標檢測框作爲landmark | Dual Quadrics from Object Detection Bounding Boxes as Landmark Representations in SLAM |
3. 傳感器相關
| 論文關鍵信息 | 論文題目 |
|---|---|
| 多傳感器標定，帶源碼 | LiDAR-Camera Calibration using 3D-3D Point correspondences |
| 多傳感器標定，激光雷達和三目相機，帶源碼 | Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor Setups |
| 傳感器網絡，綜述 | A Review of Localization and Tracking Algorithms in Wireless Sensor Networks |
| DVS，事件相機，1MHz，無結構測量模型 | Event-Based Visual Inertial Odometry |
| 深度相機 | Intel RealSense Stereoscopic Depth Cameras |
4. 地圖和重建
| 論文關鍵信息 | 論文題目 |
|---|---|
| 在OKVIS基礎上添加閉環檢測和重定位的工作 | Keyframe-Based Visual-Inertial Online SLAM with Relocalization |
| ETHZ，ROVIO，VIO，多階段建圖，地圖複用，開源代碼，ROS | maplab: An Open Framework for Research in Visual-inertial Mapping and Localization |
| 跳錶樹，時間效率高於Octomap | SkiMap: An Efficient Mapping Framework for Robot Navigation |
| todo | MapNet: Geometry-Aware Learning of Maps for Camera Localization |
| 點雲處理，模板，支持任意維度，少外部依賴，開源 | cilantro: a lean, versatile, and efficient library for point cloud data processing |
5. 數據集相關
| 論文關鍵信息 | 論文題目 |
|---|---|
| 數據集質量評估，CV-HAZOP清單 | Analyzing Computer Vision Data - The Good, the Bad and the Ugly |
| 數據集，三維重建，標註（相機位姿/平面重建/語義分割），1513個場景，250萬張圖，RGB-D採集系統 | ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes |
| 數據集，遙感圖像，OSM，武漢大學 | RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data |
| 數據集，視頻，80個AVA，人類行爲理解 | AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions |
| 數據集，目標識別，Lifelong | CoRe50: a New Dataset and Benchmark for Continuous Object Recognition |
6. 機器智能系統的嶄新研究
| 論文關鍵信息 | 論文題目 |
|---|---|
| 將GUI截屏轉爲代碼，end-to-end | pix2code: Generating Code from a Graphical User Interface Screenshot |
| 中國詩詞生成，注意力機制，記憶增強，提升美學性 | Flexible and Creative Chinese Poetry Generation Using Neural Memory |
| 司機注視點預測，ADAS，DR(eye)VE數據集 | Predicting the Driver’s Focus of Attention: the DR(eye)VE Project |
| 圖靈測試不適用於評估機器智能，標準化測試 | A Survey of Question Answering for Math and Science Problem |
7. 數學計算技術
| 論文關鍵信息 | 論文題目 |
|---|---|
| 矩陣加速 | CLBlast: A Tuned OpenCL BLAS Library |
8. 人機協作&多機協作
| 論文關鍵信息 | 論文題目 |
|---|---|
| 人人交互啓發人機交互 | Human-Robot Collaboration - From Psychology to Social Robotics |
| 多機器人系統，快速部署，廉價硬件 | Swarm-Enabling Technology for Multi-Robot Systems |
| 擁擠環境導航，合作機制建模，軌跡預測 | Modeling Cooperative Navigation in Dense Human Crowds |
| 人機協作，以統一的框架優化人、機、環境系統的最佳協作 | A Mathematical Theory of Human Machine Teaming |
9. 移動機器人 & 無人車
| 論文關鍵信息 | 論文題目 |
|---|---|
| 避障，雙目相機，深度圖劃分子區域，模糊邏輯控制器 | Obstacle Avoidance Using Stereo Camera |
其他
非線性最小二乘建模 Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Arun Das
視覺場景識別，全圖描述子 Efficient Decentralized Visual Place Recognition From Full-Image Descriptors
仿真器，物理引擎，微軟，帶源碼 AirSim - High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
遷移學習，綜述 A Cross-Dataset Recognition: A Survey
實時稠密重建，深度濾波 Video-based, real-time multi-view stereo
單目稠密重建，深度濾波，開源，REMODE，CUDA實現30FPS，Matia Pizzoli, Christian Forster and Davide Scaramuzza REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time
單目深度圖估計和運動估計，無監督，Google，David Lowe，開源，SfMLearner Unsupervised Learning of Depth and Ego-Motion from Video
長距離車輛高精度路徑跟蹤，局部平面假設先驗，單目視覺尺度修正，Tim Barfoot Monocular Visual Teach and Repeat Aided by Local Ground Planarity
單目，3D人體姿態估計，遷移學習 Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
與Peter Abbeel合作，人類行動模式啓發，認知計算模型 Robot Planning with Mathematical Models of Human State and Action