3D Point-Voxel Correlation Fields for Scene Flow Estimation
TPAMI 2023
Ziyi Wang* , Yi Wei*, Yongming Rao, Jie Zhou, Jiwen Lu
Department of Automation, Tsinghua University, China
[Paper (IEEE)] [Code (GitHub)]
we propose Point-Voxel Correlation Fields to explore relations between two consecutive point clouds and estimate scene flow that represents 3D motions.
To exploit point-based correlations, we adopt the K-Nearest Neighbors search that preserves fine-grained information in the local region, which guarantees the scene flow estimation precision.
By voxelizing point clouds in a multi-scale manner, we construct pyramid correlation voxels to model long-range correspondences, which are utilized to handle fast-moving objects.
Point-Voxel Recurrent All-Pairs Field Transforms (PV-RAFT)
Deformable PV-RAFT (DPV-RAFT)
In DPV-RAFT, we propose the Spatial Deformation that deforms the voxelized neighborhood in the voxel correlation branch.
In DPV-RAFT, we propose the Temporal Deformation that controls the iterative update process.
Experiment Results
BibTeX
@article{wang2023dpvraft,
title={3D Point-Voxel Correlation Fields for Scene Flow Estimation},
author={Wang, Ziyi and Wei, Yi and Rao, Yongming and Zhou, Jie and Lu, Jiwen},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2023},
publisher={IEEE}
}