LiFlow: Flow Matching for 3D LiDAR Scene Completion
This addresses scene completion for autonomous driving systems, offering an incremental improvement over diffusion-based methods by ensuring consistent initial distributions.
The paper tackles the problem of incomplete 3D LiDAR scenes in autonomous driving due to occlusion and sparsity by introducing a flow matching framework for scene completion, achieving state-of-the-art performance across multiple metrics.
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.