LiFlow: Flow Matching for 3D LiDAR Scene Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Matteazzi, Andrea, Tutsch, Dietmar
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910008887738368
author Matteazzi, Andrea
Tutsch, Dietmar
author_facet Matteazzi, Andrea
Tutsch, Dietmar
contents In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of incomplete 3D LiDAR scenes. Recent methods adopt local point-level denoising diffusion probabilistic models, which require predicting Gaussian noise, leading to a mismatch between training and inference initial distributions. This paper introduces the first flow matching framework for 3D LiDAR scene completion, improving upon diffusion-based methods by ensuring consistent initial distributions between training and inference. The model employs a nearest neighbor flow matching loss and a Chamfer distance loss to enhance both local structure and global coverage in the alignment of point clouds. LiFlow achieves state-of-the-art performance across multiple metrics. Code: https://github.com/matteandre/LiFlow.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02232
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LiFlow: Flow Matching for 3D LiDAR Scene Completion
Matteazzi, Andrea
Tutsch, Dietmar
Computer Vision and Pattern Recognition
In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of incomplete 3D LiDAR scenes. Recent methods adopt local point-level denoising diffusion probabilistic models, which require predicting Gaussian noise, leading to a mismatch between training and inference initial distributions. This paper introduces the first flow matching framework for 3D LiDAR scene completion, improving upon diffusion-based methods by ensuring consistent initial distributions between training and inference. The model employs a nearest neighbor flow matching loss and a Chamfer distance loss to enhance both local structure and global coverage in the alignment of point clouds. LiFlow achieves state-of-the-art performance across multiple metrics. Code: https://github.com/matteandre/LiFlow.
title LiFlow: Flow Matching for 3D LiDAR Scene Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.02232