Jun 12, 2019 · We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.

Abstract. We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.

This is the code for HPLFlowNet, a hierarchical permutohedral lattice flownet for scene flow estimation on large-scale point clouds.

Abstract. We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.

A novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds is presented and shows ...

We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.

The good performance of our method further demonstrates its capacity on large-scale point clouds, which is due to our hierarchical architecture on permutohedral ...

Hierarchical Scene Flow: HPLFlowNet [14] introduces multi-scale correlation layers by projecting the points into a permutohedral lattice as in SplatNet [46] and ...

Jan 1, 2019 · We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point ...

Hierarchical Permutohedral Lattice FlowNet for. Scene Flow Estimation on Large-scale Point Clouds ... Code released at https://github.com/laoreja/HPLFlowNet.