FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones
Xia Su, Ruiqi Chen, Jingwei Ma, Chu Li, Jon E. Froehlich
2025年份
摘要
Figure 1: We introduce FlyMeThrough, a drone-based indoor mapping system that semi-automatically maps indoor spaces and locates key facilities such as entrances, stairs, elevators, and doors. (A) We use a DJI Avata drone to scan indoor spaces, and generate reconstructed 3D maps with structure-from-motion (SfM) [40]; (B) We employ SAM2 [2] to enable intuitive and efficient user annotation of key indoor facilities. (C) FlyMeThrough auto-segments objects, generates annotations across subsequent frames, and localizes them in the 3D map, which (D) users can interactively review and update.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper17
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasZachary Teed, Jia DengNeurIPS 2021 · 被引用 1,248 次
- Nerfstudio: A Modular Framework for Neural Radiance Field DevelopmentMatthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li 等SIGGRAPH 2023 · 被引用 592 次
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) ManifoldDominic Maggio, Hyungtae Lim, Luca CarloneNeurIPS 2025 · 被引用 176 次
- RASSAR: Room Accessibility and Safety Scanning in Augmented RealityXia Su, Han Zhang, Kaiming Cheng, Jaewook Lee 等CHI 2024 · 被引用 20 次
相关 Paper
- IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor EnvironmentsXu Liu, Yu Liu, Hanshuo Qiu, Qirong Yang 等AAAI 2026 · 被引用 5 次
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and MappingJustin Lazarow, Kai Kang, Afshin DehghanNeurIPS 2025 · 被引用 2 次
- Audio-Visual Floorplan ReconstructionSenthil Purushwalkam, Sebastià Vicenc Amengual Garí, Vamsi Krishna Ithapu, Carl Schissler 等ICCV 2021 · 被引用 45 次
- Map as a By-product: Collective Landmark Mapping from IMU Data and User-provided Texts in Situated TasksRyo Yonetani, Kotaro HaraUbiComp 2025 · 被引用 1 次
- Anemoi: A Low-cost Sensorless Indoor Drone System for Automatic Mapping of 3D Airflow FieldsStephen Xia, Minghui Zhao, Charuvahan Adhivarahan, Kaiyuan Hou 等MobiCom 2023 · 被引用 6 次
