LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives
ACM Transactions on Graphics · 19.12.2024 · 43 (6) · 1-18
DOI: 10.1145/3687762 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.11.2024. Verfasst von Jiadi Cui und 9 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 105 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0). Gefördert von: National Key R&D Program of China, NSFC programs, STCSM.
Abstract (Originalsprache)
Large garages are ubiquitous yet intricate scenes that present unique challenges due to their monotonous colors, repetitive patterns, reflective surfaces, and transparent vehicle glass. Conventional Structure from Motion (SfM) methods for camera pose estimation and 3D reconstruction often fail in these environments due to poor correspondence construction. To address these challenges, we introduce LetsGo, a LiDAR-assisted Gaussian splatting framework for large-scale garage modeling and rendering. We develop a handheld scanner, Polar, equipped with IMU, LiDAR, and a fisheye camera, to facilitate accurate data acquisition. Using this Polar device, we present the GarageWorld dataset, consisting of eight expansive garage scenes with diverse geometric structures, which will be made publicly available for further research. Our approach demonstrates that LiDAR point clouds collected by the Polar device significantly enhance a suite of 3D Gaussian splatting algorithms for garage scene modeling and rendering. We introduce a novel depth regularizer that effectively eliminates floating artifacts in rendered images. Additionally, we propose a multi-resolution 3D Gaussian representation designed for Level-of-Detail (LOD) rendering. This includes adapted scaling factors for individual levels and a random-resolution-level training scheme to optimize the Gaussians across different resolutions. This representation enables efficient rendering of large-scale garage scenes on lightweight devices via a web-based renderer. Experimental results on our GarageWorld dataset, as well as on ScanNet++ and KITTI-360, demonstrate the superiority of our method in terms of rendering quality and resource efficiency.
Förderung
- National Key R&D Program of China
- NSFC programs
- STCSM
- SHMEC
- Shanghai Frontiers Science Center of Human-centered Artificial Intelligence
- MoE Key Lab of Intelligent Perception and Human-Machine Collaboration
Zitieren
APA
Cui, J., Cao, J., Zhao, F., He, Z., Chen, Y., Zhong, Y., Xu, L., Shi, Y., Zhang, Y., & Yu, J. (2024). LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives. ACM Transactions on Graphics, 43(6), 1-18. https://doi.org/10.1145/3687762
Vancouver
Cui J, Cao J, Zhao F, He Z, Chen Y, Zhong Y, et al. LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives. ACM Transactions on Graphics. 2024;43(6):1-18. doi:10.1145/3687762
BibTeX
@article{Cui2024,
author = {Cui, Jiadi and Cao, Junming and Zhao, Fuqiang and He, Zhipeng and Chen, Yifan and Zhong, Yuhui and Xu, Lan and Shi, Yujiao and Zhang, Yingliang and Yu, Jingyi},
title = {LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives},
journal = {ACM Transactions on Graphics},
year = {2024},
volume = {43},
number = {6},
pages = {1--18},
doi = {10.1145/3687762}
}
EUVIMED