Volumetric models have become a popular representation for 3D scenes in recent years. One breakthrough leading to their popularity was KinectFusion, which focuses on 3D reconstruction using RGB-D sensors. However, monocular SLAM has since also been tackled with very similar approaches. Representing the reconstruction volumetrically as a TSDF leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems. However, this representation is memory-intensive and limits applicability to small-scale reconstructions. Several avenues have been explored to overcome this. With the aim of summarizing them and providing for a fast, flexible 3D reconstruction pipeline, we propose a new, unifying framework called InfiniTAM. The idea is that steps like camera tracking, scene representation and integration of new data can easily be replaced and adapted to the user's needs.
This report describes the technical implementation details of InfiniTAM v3, the third version of our InfiniTAM system. We have added various new features, as well as making numerous enhancements to the low-level code that significantly improve our camera tracking performance. The new features that we expect to be of most interest are (i) a robust camera tracking module; (ii) an implementation of Glocker et al.'s keyframe-based random ferns camera relocaliser; (iii) a novel approach to globally-consistent TSDF-based reconstruction, based on dividing the scene into rigid submaps and optimising the relative poses between them; and (iv) an implementation of Keller et al.'s surfel-based reconstruction approach.
Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学自动化与智能感知学院);Carnegie Mellon University(卡内基梅隆大学);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院)
LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closure
School of Automation Science and Electrical Engineering, Beihang University(北京航空航天大学自动化科学与电气工程学院);Hangzhou Innovation Institute, Beihang University(北京航空航天大学杭州创新研究院);School of Mechanical Engineering, Zhejiang Sci-Tech University(浙江理工大学机械工程学院)
Loop-box: Multi-Agent Direct SLAM Triggered by Single Loop Closure for Large-Scale Mapping
Hong Kong University of Science and Technology(香港科技大学);University of California, San Diego(加利福尼亚大学圣地亚哥分校);ATG Robotics(ATG机器人技术公司);University of Bristol(布里斯托大学);Bristol Robotics Laboratory(布里斯托机器人实验室)
Department of Mechanical Engineering, State University of New York, Korea, Incheon, South Korea(纽约州立大学机械工程系);Department of Mechanical Engineering, State University of New York, Stony Brook, NY, United States(纽约州立大学石溪分校机械工程系);Department of Computer Science, State University of New York, Korea, Incheon, South Korea(纽约州立大学计算机科学系);Department of Computer Science, State University of New York, Stony Brook, NY, United States(纽约州立大学石溪分校计算机科学系)
AASS research center, Örebro University, Sweden(奥雷布罗大学AASS研究中心);Czech Technical University in Prague(布拉格捷克技术大学);Technical University of Munich, Chair: Perception for Intelligent Systems(慕尼黑技术大学感知智能系统教研室)
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
Institute for Photogrammetry and Geoinformatics, University of Stuttgart(摄影测量与地理信息学研究所,斯图加特大学);Technical University of Munich(慕尼黑技术大学);Karlsruhe University of Applied Sciences(卡尔斯鲁厄应用科学大学);Munich Center for Machine Learning(慕尼黑机器学习中心)
Reconstruction and Quantification of 3D Iris Surface for Angle-Closure Glaucoma Detection in Anterior Segment OCT
Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences(中国科学院宁波材料技术与工程研究所慈溪生物医学工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc(百度公司);Southern University of Science and Technology(南方科技大学);Zhongshan Ophthalmic Center, Sun Yat-sen University(中山大学中山眼科中心);Inception Institute of Artificial Intelligence(起源人工智能研究院)
Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods
Saarland University of Applied Science(萨尔应用科学大学);Guangxi University(广西大学);University of Florida(佛罗里达大学);Columbia University(哥伦比亚大学);Cornell University(康奈尔大学);University of Michigan(密歇根大学);Northeastern University(东北大学);Harvard University(哈佛大学);New York University(纽约大学)
Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering
Shanghai Jiao Tong University(上海交通大学);State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis(航空电子综合与航空系统体系综合国家重点实验室);Shanghai Key Laboratory of Navigation and Location Based Services(上海市导航与位置服务重点实验室);Nanyang Technological University(南洋理工大学);University of Technology Nuremberg(纽伦堡工业大学)
OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition
School of Data Science and Engineering, Xingzhi College, South China Normal University(华南师范大学行知学院数据科学与工程学院);School of Electronic and Information Engineering, South China Normal University(华南师范大学电子与信息工程学院);Hong Kong University of Science and Technology(香港科技大学);College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院);College of Electronics & Information Engineering, Shanghai Research Institu(上海电子信息工程研究院)
DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
Beihang University(北京航空航天大学);Google Inc(谷歌公司);University of Southern California(南加州大学);USC Institute for Creative Technologies(南加州大学创意技术研究所);Max-Planck-Institute for Informatics(马克斯·普朗克信息学研究所);Saarland Informatics Campus(萨尔兰信息学园区);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心);Tsinghua University(清华大学)