Multimodality Weight and Score Fusion for SLAM

Akilan, Thangarajah; Johnson, Edna; Taluja, Gaurav; Sandhu, Japneet; Chadha, Ritika

doi:10.1109/ccece47787.2020.9255714

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that pose regression approaches can be integrated into SLAM systems [2,3,21] to achieve even better accuracy and to perform fast global pose estimating, especially in cases where a global navigation satellite system is not available (e.g., indoors and urban areas with dense skyscrapers).…”

Section: Resultsmentioning

confidence: 99%

HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion

Wang,

Kang,

She

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision. LiDAR-based retrieval from a database typically incurs high computation storage costs and can lead to globally inaccurate pose estimations if the database is too sparse. On the other hand, pose regression methods take images or point clouds as inputs and directly regress global poses in an end-to-end manner. They do not perform database matching and are more computationally efficient than retrieval techniques. We propose HypLiLoc, a new model for LiDAR pose regression. We use two branched backbones to extract 3D features and 2D projection features, respectively. We consider multi-modal feature fusion in both Euclidean and hyperbolic spaces to obtain more effective feature representations. Experimental results indicate that HypLiLoc achieves state-of-the-art performance in both outdoor and indoor datasets. We also conduct extensive ablation studies on the framework design, which demonstrate the effectiveness of multi-modal feature extraction and multi-space embedding. Our code is released at: https://github.com/sijieaaa/HypLiLoc

show abstract

Section: Resultsmentioning

confidence: 99%

HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion

Wang,

Kang,

She

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Multimodal Reconstruction Different modalities have been exploited for the purpose of 3D sensing and reconstruction, include RF based [19,25,26,77,78], inertial based [53,72], and acoustic based [7,10,14,15,52,70,75]. Various applications including self-driving car [19], robot manipulation and grasping [40,65,66,68], simultaneous localiza-tion and mapping (SLAM) [1,12,51,54,57] benefited from multimodal reconstruction. Audio, given its ambient nature, has attracted unique attention in multimodal machine learning [3,17,32,39,41,48].…”

Section: Related Workmentioning

confidence: 99%

PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound

Yang

Fan²,

Isler³

et al. 2021

Preprint

View full text Add to dashboard Cite

Single view image (b) Audio (c) Metric 3D reconstruction 1m 1m * Work performed as a member of Samsung AI Center NY.a multi-stage 3D CNN that fuses audio and visual signals and learns to reconstruct 3D pose in a metric scale. We show that our multi-modal method produces accurate metric reconstruction in realworld scenes, which is not possible with state-of-the-art lifting approaches including parametric mesh regression and depth regression.

show abstract