# Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

arXiv: https://arxiv.org/abs/2305.02528 · HTML: https://mlsanity.com/paper/2305.02528/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 63 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 30 of 38)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [RAFT-3D: Scene Flow using Rigid-Motion Embeddings](https://mlsanity.com/paper/2012.00726/) (2020)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://mlsanity.com/paper/1906.05332/) (2019)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds](https://mlsanity.com/paper/2012.00987/) (2020)
- [FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.10147/) (2020)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2111.10502/) (2021)
- [FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation](https://mlsanity.com/paper/1912.01438/) (2019)
- [SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network](https://mlsanity.com/paper/2104.07861/) (2021)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://mlsanity.com/paper/2207.12394/) (2022)
- [Scene Flow from Point Clouds with or without Learning](https://mlsanity.com/paper/2011.00320/) (2020)
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://mlsanity.com/paper/2104.08683/) (2021)
- [Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion](https://mlsanity.com/paper/2009.10467/) (2020)
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk](https://mlsanity.com/paper/2105.08248/) (2021)
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://mlsanity.com/paper/2207.07522/) (2022)
- [HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding](https://mlsanity.com/paper/2105.07751/) (2021)
- [Hierarchical Attention Learning of Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/2010.05762/) (2020)
- [What Matters for 3D Scene Flow Network](https://mlsanity.com/paper/2207.09143/) (2022)
- [FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds](https://mlsanity.com/paper/2104.00798/) (2021)
- [Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds](https://mlsanity.com/paper/2203.16895/) (2022)
- [SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation](https://mlsanity.com/paper/2105.04447/) (2021)
- [Occlusion Guided Scene Flow Estimation on 3D Point Clouds](https://mlsanity.com/paper/2011.14880/) (2020)
- [Residual 3D Scene Flow Learning with Context-Aware Feature Extraction](https://mlsanity.com/paper/2109.04685/) (2021)
- [RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://mlsanity.com/paper/2204.00354/) (2022)

## Built on by (most cited first, 24 of 24)

- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving](https://mlsanity.com/paper/2407.01702/) (2024)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow](https://mlsanity.com/paper/2403.07432/) (2024)
- [DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model](https://mlsanity.com/paper/2311.17456/) (2023)
- [SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection](https://mlsanity.com/paper/2312.13641/) (2023)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision](https://mlsanity.com/paper/2401.02550/) (2024)
- [Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals](https://mlsanity.com/paper/2401.11499/) (2024)
- [Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering](https://mlsanity.com/paper/2404.08363/) (2024)
- [NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation](https://mlsanity.com/paper/2405.14241/) (2024)
- [Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior](https://mlsanity.com/paper/2310.11284/) (2023)
- [GERA: Geometric Embedding for Efficient Point Registration Analysis](https://mlsanity.com/paper/2410.00589/) (2024)
- [Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving](https://mlsanity.com/paper/2509.13116/) (2025)
- [RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving](https://mlsanity.com/paper/2511.12117/) (2025)
- [Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency](https://mlsanity.com/paper/2312.08879/) (2023)
- [SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label](https://mlsanity.com/paper/2312.15271/) (2023)
- [Fast Kernel Scene Flow](https://mlsanity.com/paper/2403.05896/) (2024)
- [CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario](https://mlsanity.com/paper/2404.10571/) (2024)
- [Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss](https://mlsanity.com/paper/2410.11934/) (2024)
- [STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow](https://mlsanity.com/paper/2403.07032/) (2024)
- [Long-Term 3D Point Tracking By Cost Volume Fusion](https://mlsanity.com/paper/2407.13337/) (2024)
- [SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flow](https://mlsanity.com/paper/2408.07825/) (2024)
- [UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration](https://mlsanity.com/paper/2410.22909/) (2024)

## Abstract (arXiv)

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D scenes for scene flow estimation. However, in existing methods, superpoints are generated with the offline clustering methods, which cannot characterize local regions with similar motions for complex 3D scenes well, leading to inaccurate scene flow estimation. To this end, we propose an iterative end-to-end superpoint based scene flow estimation framework, where the superpoints can be dynamically updated to guide the point-level flow prediction. Specifically, our framework consists of a flow guided superpoint generation module and a superpoint guided flow refinement module. In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds. With the generated superpoints, we first reconstruct the flow for each point by adaptively aggregating the superpoint-level flow, and then encode the consistency between the reconstructed flow of pairwise point clouds. Finally, we feed the consistency encoding along with the reconstructed flow into GRU to refine point-level flow. Extensive experiments on several different datasets show that our method can achieve promising performance.