Accurate Implicit Neural Mapping With More Compact Representation in Large-Scale Scenes Using Ranging Data | |
Shi, Chenhui1,2; Tang, Fulin2; Wu, Yihong1,2; Jin, Xin3; Ma, Gang3 | |
刊名 | IEEE ROBOTICS AND AUTOMATION LETTERS |
2023-10-01 | |
卷号 | 8期号:10页码:6683-6690 |
关键词 | Implicit neural mapping large-scale scenes ranging data |
ISSN号 | 2377-3766 |
DOI | 10.1109/LRA.2023.3311355 |
通讯作者 | Tang, Fulin(fulin.tang@nlpr.ia.ac.cn) ; Wu, Yihong(yhwu@nlpr.ia.ac.cn) |
英文摘要 | Large-scale 3D mapping nowadays is a research hotspot in robotics. A greatly concerning issue is reconstructing high-accuracy maps in a hardware environment with limited memory. To address this problem, we propose a novel implicit neural mapping approach with higher accuracy and less memory. It first adopts an improved hierarchical hash encoder, independent of geometric bounding (e.g., bounding box or sphere), for a more compact map representation, and then leverages a spatial hash grid to restrict the encoding space to the proximity of geometric surfaces, preventing hash collisions between encoding in free space and near geometric surfaces. The hash grid indexes the scene point cloud produced by ranging data. Through a tiny MLP, features encoded from sampled points in the hash grid can be converted to truncated signed distance values. To further improve mapping accuracy, a new method is developed to instantly obtain more accurate signed distance labels from ranging data by computing the closest distances from sampled points to the point cloud indexed by the constructed hash grid, not just the distances from sampled points to geometric surfaces along rays, and then use these labels to supervise the learning of our hash encoder. Experimental evaluations performed on large-scale indoor and outdoor datasets demonstrate that our approach achieves state-of-the-art mapping performance with less than half of the memory consumption compared with previous advanced 3D mapping methods using ranging data. |
资助项目 | National Key R&D Program of China ; National Natural Science Foundation of China[2022YFB3303202] ; National Natural Science Foundation of China[62202468] ; [62002359] |
WOS研究方向 | Robotics |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001081606600002 |
资助机构 | National Key R&D Program of China ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53062] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Tang, Fulin; Wu, Yihong |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Huawei Cloud EI Innovat Lab, Beijing 100085, Peoples R China |
推荐引用方式 GB/T 7714 | Shi, Chenhui,Tang, Fulin,Wu, Yihong,et al. Accurate Implicit Neural Mapping With More Compact Representation in Large-Scale Scenes Using Ranging Data[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2023,8(10):6683-6690. |
APA | Shi, Chenhui,Tang, Fulin,Wu, Yihong,Jin, Xin,&Ma, Gang.(2023).Accurate Implicit Neural Mapping With More Compact Representation in Large-Scale Scenes Using Ranging Data.IEEE ROBOTICS AND AUTOMATION LETTERS,8(10),6683-6690. |
MLA | Shi, Chenhui,et al."Accurate Implicit Neural Mapping With More Compact Representation in Large-Scale Scenes Using Ranging Data".IEEE ROBOTICS AND AUTOMATION LETTERS 8.10(2023):6683-6690. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论