专栏名称: 3DCV

关注工业3D视觉、SLAM、自动驾驶技术，更专注3D视觉产业的信息传播和产品价值的创造，深度聚焦于3D视觉传感器、SLAM产品，使行业产品快速连接消费者。

顶会顶刊最全总结！激光视觉融合SLAM资源汇总

3DCV · 公众号 · · 2024-07-18 11:00

正文

点击下方卡片，关注 「3D视觉工坊」 公众号
选择星标，干货第一时间送达

来源：3D视觉工坊

添加小助理：dddvision，备注：方向+学校/公司+昵称，拉你入群。文末附行业细分群

扫描下方二维码，加入 3D视觉知识星球，星球内凝聚了众多3D视觉实战问题，以及各个模块的学习资料：近20门视频课程（星球成员免费学习）、最新顶会论文、计算机视觉书籍、优质3D视觉算法源码等。想要入门3D视觉、做项目、搞科研，欢迎扫码加入！

作者: 殷杰毕业于上海交通大学，曾在ICRA，IROS，RAL等机器人顶会/期刊上发表多篇成果

详情请参照原链接： https://github.com/sjtuyinjie/awesome-LiDAR-Visual-SLAM ,更新中。整理不易，请多多star和fork.

LiDAR-Visual-Fusion SLAM(同步定位与地图构建)技术结合了LiDAR(激光雷达)和视觉传感器的优势，能够在复杂环境中实现高精度的定位和地图构建。相较于单一的LiDAR或视觉SLAM系统，LiDAR-Visual-Fusion SLAM具有更强的鲁棒性和准确性，尤其在光线变化、动态环境或结构复杂的场景中表现出色。近年来，随着传感器技术和算法的不断进步，LiDAR-Visual-Fusion SLAM在自动驾驶、无人机导航、机器人等领域得到了广泛应用和快速发展。

这是一个关于LiDAR-Visual-Fusion-SLAM的资源汇总列表，我会不定期更新这个页面。如果这个项目对您的研究有帮助，请给我一个star并fork，谢谢！如果您的LiDAR-Visual-SLAM相关工作被顶级会议或期刊接收，欢迎提issue提醒我更新您的工作！

论文汇总

2024

[RAL2024] LIVER: A Tightly Coupled LiDAR-Inertial-Visual State Estimator With High Robustness for Underground Environments

paper: https://ieeexplore.ieee.org/abstract/document/10404014
code: https://github.com/ZikangYuan/sr_livo

[RAL2024] A LiDAR-inertial-visual odometry and mapping system based on the sweep reconstruction method

paper: https://xplorestaging.ieee.org/document/10501952
code: https://github.com/ZikangYuan/sr_livo

[RAL2024] LVIO-Fusion LiDAR-Visual-Inertial Odometry and Mapping in Degenerate Environments

paper: https://ieeexplore.ieee.org/abstract/document/10452777

[TRO2024 under review] FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

paper: https://ieeexplore.ieee.org/document/9739244
code: https://github.com/hku-mars/FAST-LIVO2

[TPAMI2024 under review] R3LIVE++: A Robust, Real-time, Radiance reconstruction package with a tightly-coupled LiDAR-Inertial-Visual state Estimator

paper: https://arxiv.org/abs/2209.03666
code: https://github.com/hku-mars/r3live

[TIM2024] Dynam-LVIO: A Dynamic-Object-Aware LiDAR Visual Inertial Odometry in Dynamic Urban Environments

paper: https://ieeexplore.ieee.org/document/10511062

[Remote Sensing2024] LVI-Fusion: A Robust Lidar-Visual-Inertial SLAM Scheme

paper: https://www.mdpi.com/2072-4292/16/9/1524

2023

[TPAMI2023] SDV-LOAM: Semi-Direct Visual–LiDAR Odometry and Mapping

paper: https://ieeexplore.ieee.org/abstract/document/10086694
code: https://github.com/ZikangYuan/SDV-LOAM

[RAL2023] Coco-LIC: Continuous-Time Tightly-Coupled LiDAR-Inertial-Camera Odometry using Non-Uniform B-spline

paper: https://arxiv.org/pdf/2309.09808
code: https://github.com/APRIL-ZJU/Coco-LIC

2022

[IROS2022] Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry

paper: https://ieeexplore.ieee.org/document/9739244
code: https://github.com/hku-mars/FAST-LIVO

[ICRA2022] R3LIVE: A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

paper: https://ieeexplore.ieee.org/document/9811935
code: https://github.com/hku-mars/r3live

[RAL2022] mvil-fusion: Monocular visual-inertial-lidar simultaneous localization and mapping in challenging environments

paper: https://ieeexplore.ieee.org/abstract/document/9968060

2021

[RAL2021] R2LIVE: A Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping

paper: https://github.com/hku-mars/r2live/blob/master/paper/r2live_ral_final.pdf```
code: https://github.com/hku-mars/r2live

[IROS2021] Lvio-Fusion: A Self-adaptive Multi-sensor Fusion SLAM Framework Using Actor-critic Method

paper: https://arxiv.org/abs/2106.06783
code: ```https://github.com/jypjypjypjyp/lvio_fusion

[ICRA2021] CamVox: A Low-cost and Accurate Lidar-assisted Visual SLAM System
paper: https://ieeexplore.ieee.org/abstract/document/9561149
code: https://github.com/ISEE-Technology/CamVox
[ICRA2021] LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping

paper: https://github.com/TixiaoShan/LVI-SAM/blob/master/doc/paper.pdf
code: https://github.com/TixiaoShan/LVI-SAM

[TIV2021] Efficient and Accurate Tightly-Coupled Visual-Lidar SLAM

paper: https://ieeexplore.ieee.org/abstract/document/9632274

[ROBIO2021] LVIO-SAM: A Multi-sensor Fusion Odometry via Smoothing and Mapping

paper: https://ieeexplore.ieee.org/document/9739244
code: https://github.com/TurtleZhong/LVIO-SAM

[Remote Sensing2021] DV-LOAM: Direct Visual LiDAR Odometry and Mapping

paper: https://www.mdpi.com/2072-4292/13/16/3340
code: https://github.com/kinggreat24/dv-loam

2020

[IROS2020] LIC-Fusion 2.0: LiDAR-Inertial-Camera Odometry with Sliding-Window Plane-Feature Tracking

paper: https://arxiv.org/pdf/2008.07196

[ICRA2020] Lidar-Monocular Visual Odometry using Point and Line Features

paper: https://ieeexplore.ieee.org/abstract/document/9196613

[Automomous Robots2020] DVL-SLAM: sparse depth enhanced direct visual-LiDAR SLAM

paper: https://link.springer.com/article/10.1007/s10514-019-09881-0

2019

[IROS2019] LIC-Fusion: LiDAR-Inertial-Camera Odometry

paper: https://ieeexplore.ieee.org/xpl/conhome/8957008/proceeding

[IROS2019] ViLiVO: Virtual LiDAR-Visual Odometry for an Autonomous Vehicle with a Multi-Camera System

paper: https://ieeexplore.ieee.org/abstract/document/8968484

2018

[IROS2018] LIMO: Lidar-Monocular Visual Odometry

paper: https://ieeexplore.ieee.org/abstract/document/8594394
code: https://github.com/johannes-graeter/limo

相关的awesome-lists

awesome-SLAM: https://github.com/SilenceOverflow/Awesome-SLAM

awesome-SLAM-datasets: https://github.com/youngguncho/awesome-slam-datasets

Awesome-Implicit-NeRF-Robotics: https://github.com/zubair-irshad/Awesome-Implicit-NeRF-Robotics

awesome-humanoid-learning: https://github.com/jonyzhang2023/awesome-humanoid-learning

awesome-isaac-gym: https://github.com/wangcongrobot/awesome-isaac-gym

Awesome_Quadrupedal_Robots: https://github.com/curieuxjy/Awesome_Quadrupedal_Robots

Awesome Robot Descriptions: https://github.com/robot-descriptions/awesome-robot-descriptions

awesome-legged-locomotion-learning: https://github.com/gaiyi7788/awesome-legged-locomotion-learning

本文仅做学术分享，如有侵权，请联系删文。

3D视觉工坊交流群

目前我们已经建立了3D视觉方向多个社群，包括 2D计算机视觉 、 大模型 、 工业3D视觉 、 SLAM 、 自动驾驶 、 三维重建 、 无人机 等方向，细分群包括：

2D计算机视觉： 图像分类/分割、目标/检测、医学影像、GAN、OCR、2D缺陷检测、遥感测绘、超分辨率、人脸检测、行为识别、模型量化剪枝、迁移学习、人体姿态估计等

大模型： NLP、CV、ASR、生成对抗大模型、强化学习大模型、对话大模型等

工业3D视觉： 相机标定、立体匹配、三维点云、结构光、机械臂抓取、缺陷检测、6D位姿估计、相位偏折术、Halcon、摄影测量、阵列相机、光度立体视觉等。

SLAM ： 视觉SLAM、激光SLAM、语义SLAM、滤波算法、多传感器融合、多传感器标定、动态SLAM、MOT SLAM、NeRF SLAM、机器人导航等。

自动驾驶： 深度估计、Transformer、毫米波|激光雷达|视觉摄像头传感器、多传感器标定、多传感器融合、自动驾驶综合群等、3D目标检测、路径规划、轨迹预测、3D点云分割、模型部署、车道线检测、Occupancy、目标跟踪等。

三维重建： 3DGS、NeRF、多视图几何、OpenMVS、MVSNet、colmap、纹理贴图等

无人机： 四旋翼建模、无人机飞控等

除了这些，还有求职、 硬件选型 、 视觉产品落地 、 最新论文 、 3D视觉最新产品 、 3D视觉行业新闻 等交流群

添加小助理: dddvision，备注： 研究方向+学校/公司+昵称 （如3D点云+清华+小草莓） , 拉你入群。

3D视觉工坊知识星球

3D视觉从入门到精通知识星球、国内成立最早、6000+成员交流学习。包括： 星球视频课程近20门（价值超6000） 、 项目对接 、 3D视觉学习路线总结 、 最新顶会论文&代码 、 3D视觉行业最新模组 、 3D视觉优质源码汇总