Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels
This addresses the challenge of expensive ground-truth annotation for scene flow in point clouds, offering a more efficient solution for applications like robotics and autonomous driving, though it is incremental as it builds on existing self-supervised approaches.
The paper tackles the problem of estimating 3D scene flow from point clouds without ground-truth annotations by generating pseudo labels using monocular RGB images and point clouds, and it achieves results that outperform state-of-the-art self-supervised and some supervised methods.
We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations. Due to the irregularity and sparsity of point clouds, it is expensive and time-consuming to acquire ground-truth scene flow annotations. Some state-of-the-art approaches train scene flow networks in a self-supervised learning manner via approximating pseudo scene flow labels from point clouds. However, these methods fail to achieve the performance level of fully supervised methods, due to the limitations of point cloud such as sparsity and lacking color information. To provide an alternative, we propose a novel approach that utilizes monocular RGB images and point clouds to generate pseudo scene flow labels for training scene flow networks. Our pseudo label generation module infers pseudo scene labels for point clouds by jointly leveraging rich appearance information in monocular images and geometric information of point clouds. To further reduce the negative effect of noisy pseudo labels on the training, we propose a noisy-label-aware training scheme by exploiting the geometric relations of points. Experiment results show that our method not only outperforms state-of-the-art self-supervised approaches, but also outperforms some supervised approaches that use accurate ground-truth flows.