NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation

C Jiang, D Du, J Liu, S Zhu, Z Liu, Z Ma, Z Liang… - arxiv preprint arxiv …, 2024 - arxiv.org
Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal
dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal …

Monocular 3D object detection with thermodynamic loss and decoupled instance depth

G Liu, X **e, Q Yu - Connection Science, 2024 - Taylor & Francis
Monocular 3D detection is to obtain the 3D information of the object from the image. The
mainstream methods mainly use L1 loss or L1-like loss to control the instance depth …

Image-to-Point Registration via Cross-Modality Correspondence Retrieval

L Bie, S Li, K Cheng - Proceedings of the 2024 International Conference …, 2024 - dl.acm.org
Image-to-Point Cloud registration between 2D images and 3D LiDAR point clouds is a
significant task in computer vision. The traditional registration pipeline first establishes …

Build a Cross-modality Bridge for Image-to-Point Cloud Registration

L Bie, S Pan, K Cheng, L Han - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Although the fusion of images and LiDAR point clouds is crucial to many applications in
computer vision, the relative poses of cameras and LiDAR scanners often need to be …

Low-Cost Fusion Odometry Algorithm Based on 4D Radar and Pseudo-LiDAR: Bridging the Gap between 4D Radar and Images in 3D Space

M Huang, S Lu, G Zhuo - 2024 - sae.org
Abstract Recently, four-dimensional (4D) radar has shown unique advantages in the field of
odometry estimation due to its low cost, all-weather use, and dynamic and static recognition …

[PDF][PDF] DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment (Supplementary Materials)

J Liu, D Zhuo, Z Feng, S Zhu, C Peng, Z Liu, H Wang - fq.pkwyx.com
In this supplementary material, we provide additional details about our network and show
more experimental results of the proposed methods. In Sec. 1, we illustrate more …