论文阅读《DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS》本论文提出了一种具有神经隐式映射表示的稠密RGB SLAM。该方案不需要深度输入，并且不需要任何预训练模型。为了实现这一目标，本文引入了一个分层的特

论文阅读《ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras》本文提出了ORB-SLAM2，它是基于单目、双目或RGB-D相机的一个完整

Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding回顾iMAP 这篇工作很大部分都基于iMAP，去年暑假我翻译了这篇论文 使用隐式神经场

CS231A Lecture 9：Fitting and Matching lecture 9 也没什么内容，不过还是好好记一下，霍夫变换之前不太了解。。。 Reading: [HZ] Chapter: 4 “Estimation –

CS231A Lecture 7：Multi-view geometry (2) Reading: [HZ] Chapter 10 “3D reconstruction of cameras and structure” [HZ] Cha

CS231A Lecture 7：Multi-view geometry (1) Reading: [HZ] Chapter 10 “3D reconstruction of cameras and structure” [HZ] Cha

CS231A Lecture 6：Stereo Systems Reading: [HZ] Chapter: 9 “Epip. Geom. and the Fundam. Matrix Transf.” [HZ] Chapter: 18

CS231A Lecture 5：Epipolar Geometry Reading: [HZ] Chapter: 4 “Estimation – 2D perspective transformations [HZ] Chapter:

CS231A Lecture 4：Single View Metrology Reading: [HZ] Chapter 2 “Projective Geometry and Transformation in 2D” [HZ] Chapt

CS231A Lecture 3：Camera Calibration Reading: [FP] Chapter 1 “Geometric Camera Calibration” [HZ] Chapter 7 “Computation

CS231A Lecture 2: Camera Models Reading: [FP] Chapter 1, “Geometric Camera Models” [HZ] Chapter 6 “Camera Models”

论文阅读《iMAP: Implicit Mapping and Positioning in Real-Time 》Abstract我们首次展示了多层感知器 (MLP) 可以作为手持 RGB-D 相机的实时 SLAM 系统中唯一的场景表示。