# Hierarchical Attention Learning of Scene Flow in 3D Point Clouds

arXiv: https://arxiv.org/abs/2010.05762 · HTML: https://mlsanity.com/paper/2010.05762/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 30 of 35)

- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://mlsanity.com/paper/2303.12384/) (2023)
- [What Matters for 3D Scene Flow Network](https://mlsanity.com/paper/2207.09143/) (2022)
- [Efficient 3D Deep LiDAR Odometry](https://mlsanity.com/paper/2111.02135/) (2021)
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [3D Object Detection with a Self-supervised Lidar Scene Flow Backbone](https://mlsanity.com/paper/2205.00705/) (2022)
- [D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction](https://mlsanity.com/paper/2205.01135/) (2022)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [Residual 3D Scene Flow Learning with Context-Aware Feature Extraction](https://mlsanity.com/paper/2109.04685/) (2021)
- [DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds](https://mlsanity.com/paper/2308.04383/) (2023)
- [RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://mlsanity.com/paper/2204.00354/) (2022)
- [Multi-Body Neural Scene Flow](https://mlsanity.com/paper/2310.10301/) (2023)
- [DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model](https://mlsanity.com/paper/2311.17456/) (2023)
- [End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization](https://mlsanity.com/paper/2306.11346/) (2023)
- [Unsupervised Learning of 3D Scene Flow from Monocular Camera](https://mlsanity.com/paper/2206.03673/) (2022)
- [3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion](https://mlsanity.com/paper/2209.13130/) (2022)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix](https://mlsanity.com/paper/2312.08009/) (2023)
- [Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations](https://mlsanity.com/paper/2403.13261/) (2024)
- [FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation](https://mlsanity.com/paper/2412.17366/) (2024)
- [HDMNet: A Hierarchical Matching Network with Double Attention for Large-scale Outdoor LiDAR Point Cloud Registration](https://mlsanity.com/paper/2310.18874/) (2023)
- [TARS: Traffic-Aware Radar Scene Flow Estimation](https://mlsanity.com/paper/2503.10210/) (2025)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance](https://mlsanity.com/paper/2209.04945/) (2022)
- [Viewport Prediction for Volumetric Video Streaming by Exploring Video Saliency and Trajectory Information](https://mlsanity.com/paper/2311.16462/) (2023)
- [PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds](https://mlsanity.com/paper/2302.14193/) (2023)
- [Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point Clouds](https://mlsanity.com/paper/2303.02454/) (2023)
- [CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario](https://mlsanity.com/paper/2404.10571/) (2024)
- [RMS-FlowNet++: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://mlsanity.com/paper/2407.01129/) (2024)
- [DNOI-4DRO: Deep 4D Radar Odometry with Differentiable Neural-Optimization Iterations](https://mlsanity.com/paper/2505.12310/) (2025)

## Abstract (arXiv)

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous driving and service robot. This paper studies the problem of scene flow estimation from two consecutive 3D point clouds. In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer. The proposed network has a new more-for-less hierarchical architecture. The more-for-less means that the number of input points is greater than the number of output points for scene flow estimation, which brings more input information and balances the precision and resource consumption. In this hierarchical architecture, scene flow of different levels is generated and supervised respectively. A novel attentive embedding module is introduced to aggregate the features of adjacent points using a double attention method in a patch-to-patch manner. The proper layers for flow embedding and flow supervision are carefully considered in our network designment. Experiments show that the proposed network outperforms the state-of-the-art performance of 3D scene flow estimation on the FlyingThings3D and KITTI Scene Flow 2015 datasets. We also apply the proposed network to realistic LiDAR odometry task, which is an key problem in autonomous driving. The experiment results demonstrate that our proposed network can outperform the ICP-based method and shows the good practical application ability.