# Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

arXiv: https://arxiv.org/abs/2203.16895 · HTML: https://mlsanity.com/paper/2203.16895/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 58 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 30 of 36)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Train in Germany, Test in The USA: Making 3D Object Detectors Generalize](https://mlsanity.com/paper/2005.08139/) (2020)
- [Learning from Synthetic Data for Crowd Counting in the Wild](https://mlsanity.com/paper/1903.03303/) (2019)
- [xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/1911.12676/) (2019)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [No More Discrimination: Cross City Adaptation of Road Scene Segmenters](https://mlsanity.com/paper/1704.08509/) (2017)
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://mlsanity.com/paper/1906.05332/) (2019)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [Just Go with the Flow: Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/1912.00497/) (2019)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [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)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)

## Built on by (most cited first, 28 of 28)

- [Fast Neural Scene Flow](https://mlsanity.com/paper/2304.09121/) (2023)
- [ICP-Flow: LiDAR Scene Flow Estimation with ICP](https://mlsanity.com/paper/2402.17351/) (2024)
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [Re-Evaluating LiDAR Scene Flow for Autonomous Driving](https://mlsanity.com/paper/2304.02150/) (2023)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2303.12535/) (2023)
- [ZeroFlow: Scalable Scene Flow via Distillation](https://mlsanity.com/paper/2305.10424/) (2023)
- [Multi-Body Neural Scene Flow](https://mlsanity.com/paper/2310.10301/) (2023)
- [Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation](https://mlsanity.com/paper/2310.15676/) (2023)
- [VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow](https://mlsanity.com/paper/2503.22328/) (2025)
- [Progressive Transformation Learning for Leveraging Virtual Images in Training](https://mlsanity.com/paper/2211.01778/) (2022)
- [3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion](https://mlsanity.com/paper/2209.13130/) (2022)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation](https://mlsanity.com/paper/2605.26500/) (2026)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [Zero-shot detection of buildings in mobile LiDAR using Language Vision Model](https://mlsanity.com/paper/2404.09931/) (2024)
- [Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection](https://mlsanity.com/paper/2404.11737/) (2024)
- [RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Clouds](https://mlsanity.com/paper/2512.10376/) (2025)
- [Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance](https://mlsanity.com/paper/2209.04945/) (2022)
- [Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior](https://mlsanity.com/paper/2310.11284/) (2023)
- [A denoised Mean Teacher for domain adaptive point cloud registration](https://mlsanity.com/paper/2306.14749/) (2023)
- [Fast Kernel Scene Flow](https://mlsanity.com/paper/2403.05896/) (2024)
- [Synthetic-to-Real Translation for Class-Agnostic Motion Prediction](https://mlsanity.com/paper/2607.06319/) (2026)
- [G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection](https://mlsanity.com/paper/2607.19942/) (2026)
- [ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs](https://mlsanity.com/paper/2607.20670/) (2026)
- [CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2607.29237/) (2026)
- [RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2608.18864/) (2026)

## Abstract (arXiv)

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real scenes. However, large disparities between existing synthetic datasets and real scenes lead to poor model transfer. We make two major contributions to address that. First, we develop a point cloud collector and scene flow annotator for GTA-V engine to automatically obtain diverse realistic training samples without human intervention. With that, we develop a large-scale synthetic scene flow dataset GTA-SF. Second, we propose a mean-teacher-based domain adaptation framework that leverages self-generated pseudo-labels of the target domain. It also explicitly incorporates shape deformation regularization and surface correspondence refinement to address distortions and misalignments in domain transfer. Through extensive experiments, we show that our GTA-SF dataset leads to a consistent boost in model generalization to three real datasets (i.e., Waymo, Lyft and KITTI) as compared to the most widely used FT3D dataset. Moreover, our framework achieves superior adaptation performance on six source-target dataset pairs, remarkably closing the average domain gap by 60%. Data and codes are available at https://github.com/leolyj/DCA-SRSFE