KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done the Right Way

Vizzo, Ignacio; Guadagnino, Tiziano; Mersch, Benedikt; Wiesmann, Louis; Behley, Jens; Stachniss, Cyrill

doi:10.1109/lra.2023.3236571

Cited by 168 publications

(58 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Poisson surface reconstruction SLAM method Puma [36], a TSDF fusion-based approach Vdbfusion [37], and an implicit neural networkbased map representation SHINE-Mapping [50]. Since both Vdbfusion and SHINE-Mapping only focus on dense mapping, we combine them with the current SOTA odometry method KissICP [38]. For fair comparison, we also show the results of our methods using KissICP poses.…”

Section: Simultaneously Odometry and Mapping Resultsmentioning

confidence: 99%

See 1 more Smart Citation

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Deng¹,

Chen²,

Xia³

et al. 2023

Preprint

View full text Add to dashboard Cite

Simultaneously odometry and mapping using LiDAR data is an important task for mobile systems to achieve full autonomy in large-scale environments. However, most existing LiDAR-based methods prioritize tracking quality over reconstruction quality. Although the recently developed neural radiance fields (NeRF) have shown promising advances in implicit reconstruction for indoor environments, the problem of simultaneous odometry and mapping for large-scale scenarios using incremental LiDAR data remains unexplored. To bridge this gap, in this paper, we propose a novel NeRF-based LiDAR odometry and mapping approach, NeRF-LOAM, consisting of three modules neural odometry, neural mapping, and mesh reconstruction. All these modules utilize our proposed neural signed distance function, which separates LiDAR points into ground and non-ground points to reduce Z-axis drift, optimizes odometry and voxel embeddings concurrently, and in the end generates dense smooth mesh maps of the environment. Moreover, this joint optimization allows our NeRF-LOAM to be pre-trained free and exhibit strong generalization abilities when applied to different environments. Extensive evaluations on three publicly available datasets demonstrate that our approach achieves state-of-the-art odometry and mapping performance, as well as a strong generalization in large-scale environments utilizing LiDAR data. Furthermore, we perform multiple ablation studies to validate the effectiveness of our network design. The implementation of our approach will be made available at https: //github.com/JunyuanDeng/NeRF-LOAM .

show abstract

Section: Simultaneously Odometry and Mapping Resultsmentioning

confidence: 99%

“…13 and Fig. 14 the mapping results on MaiCity dataset of SHINE-Mapping [50] and Vdbfusion [37] combined with KissICP [38] odometry. These results also demonstrate that ours can provide a complete and smooth map.…”

Section: A Simultaneously Odometry and Mapping Resultsmentioning

confidence: 99%

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Deng¹,

Chen²,

Xia³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Our solution provides 3D data with new unique characteristics: omnidirectionality and non repetitive pattern. Those two characteristics can be beneficial in mapping alogorithms without odometry, such as lidar inertial odometry [ 45 ], lidar inertial mapping and smoothing [ 42 ], or modern approaches to ego motion estimation [ 47 ].…”

Section: Discussionmentioning

confidence: 99%

Affordable Robotic Mobile Mapping System Based on Lidar with Additional Rotating Planar Reflector

Bedkowski

Pełka²

2023

Sensors

View full text Add to dashboard Cite

This paper describes an affordable robotic mobile 3D mapping system. It is built with Livox Mid−40 lidar with a conic field of view extended by a custom rotating planar reflector. This 3D sensor is compared with the more expensive Velodyne VLP 16 lidar. It is shown that the proposed sensor reaches satisfactory accuracy and range. Furthermore, it is able to preserve the metric accuracy and non−repetitive scanning pattern of the unmodified sensor. Due to preserving the non−repetitive scan pattern, our system is capable of covering the entire field of view of 38.4 × 360 degrees, which is an added value of conducted research. We show the calibration method, mechanical design, and synchronization details that are necessary to replicate our system. This work extends the applicability of solid−state lidars since the field of view can be reshaped with minimal loss of measurement properties. The solution was part of a system that was evaluated during the 3rd European Robotics Hackathon in the Zwentendorf Nuclear Power Plant. The experimental part of the paper demonstrates that our affordable robotic mobile 3D mapping system is capable of providing 3D maps of a nuclear facility that are comparable to the more expensive solution.

show abstract

“…LiDAR odometry generally employs scan-matching techniques including ICP, KISS-ICP [16], GICP [17], and others to determine the relative transformation between two successive frames. Feature-based matching approaches have gained popularity as a computationally efficient alternative to full point cloud matching.…”

Section: Related Workmentioning

confidence: 99%

Robust Multi-Modal Multi-LiDAR-Inertial Odometry and Mapping for Indoor Environments

Li¹,

Yu²,

Queralta³

et al. 2023

Preprint

View full text Add to dashboard Cite

KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done the Right Way

Cited by 168 publications

References 33 publications

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Affordable Robotic Mobile Mapping System Based on Lidar with Additional Rotating Planar Reflector

Robust Multi-Modal Multi-LiDAR-Inertial Odometry and Mapping for Indoor Environments

Contact Info

Product

Resources

About