
Photo-SLAM is a novel SLAM framework that maintains a hyper primitives map to efficiently optimize tracking using a factor graph solver and learn the corresponding mapping by backpropagating the loss between the original images and rendering images. It introduces geometry-based densification and Gaussian-Pyramid-based learning to enhance online photorealistic mapping performance.


coremsg

real-time-simultaneous-localization-and-photorealistic-mapping-for-monocular-stereo-and-rgb-d-cameras


Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras


title_rewrite


BundledSLAM is a visual SLAM system that efficiently fuses data from multiple synchronized cameras to achieve highly accurate pose estimation and mapping.


bundledslam-an-accurate-and-comprehensive-visual-slam-system-using-multiple-synchronized-cameras


BundledSLAM: An Accurate and Comprehensive Visual SLAM System Using Multiple Synchronized Cameras
