Occlusion Guided Scene Flow Estimation on 3D Point Clouds
This work addresses the problem of accurate 3D scene flow estimation for autonomous systems and robotics, particularly in the presence of occlusions in sparse point cloud data.
This paper introduces OGSF-Net, a novel architecture for 3D scene flow estimation that integrates the learning of both flow and occlusions between frames. This coupled approach leads to improved accuracy in flow prediction, achieving state-of-the-art results on the Flyingthings3D and KITTI datasets.
3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a new scene flow architecture called OGSF-Net which tightly couples the learning for both flow and occlusions between frames. Their coupled symbiosis results in a more accurate prediction of flow in space. Unlike a traditional multi-action network, our unified approach is fused throughout the network, boosting performances for both occlusion detection and flow estimation. Our architecture is the first to gauge the occlusion in 3D scene flow estimation on point clouds. In key datasets such as Flyingthings3D and KITTI, we achieve the state-of-the-art results.