Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation

TL;DR

Flow4D introduces a 4D voxel network with a novel spatio-temporal fusion approach for LiDAR scene flow estimation, significantly improving accuracy while maintaining real-time performance.

Contribution

The paper proposes Flow4D, a new method that explicitly models spatio-temporal features using a 4D voxel network and a novel STDB for efficiency, advancing LiDAR scene flow estimation.

Findings

Achieves 45.9% higher performance than state-of-the-art methods.

Utilizes five frames for richer temporal context.

Wins 1st place in the 2024 Argoverse 2 Scene Flow Challenge.

Abstract

Understanding the motion states of the surrounding environment is critical for safe autonomous driving. These motion states can be accurately derived from scene flow, which captures the three-dimensional motion field of points. Existing LiDAR scene flow methods extract spatial features from each point cloud and then fuse them channel-wise, resulting in the implicit extraction of spatio-temporal features. Furthermore, they utilize 2D Bird's Eye View and process only two frames, missing crucial spatial information along the Z-axis and the broader temporal context, leading to suboptimal performance. To address these limitations, we propose Flow4D, which temporally fuses multiple point clouds after the 3D intra-voxel feature encoder, enabling more explicit extraction of spatio-temporal features through a 4D voxel network. However, while using 4D convolution improves performance, it significantly increases the computational load. For further efficiency, we introduce the Spatio-Temporal Decomposition Block (STDB), which combines 3D and 1D convolutions instead of using heavy 4D convolution. In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information. As a result, the proposed method achieves a 45.9% higher performance compared to the state-of-the-art while running in real-time, and won 1st place in the 2024 Argoverse 2 Scene Flow Challenge. The code is available at https://github.com/dgist-cvlab/Flow4D.