mlsanityData to 7 Oct 2026

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

arXiv 2209.13130 ↗First posted 27 Sep 2022cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

22 of 36 references.

References · 22

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  3. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  4. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  5. 2018Pyramid Stereo Matching Networkcited by 486
  6. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  7. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  8. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  9. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  10. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  11. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 121
  12. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
10 more
  1. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  2. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  3. 2020Scene Flow from Point Clouds with or without Learningcited by 44
  4. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  5. 2020Hierarchical Attention Learning of Scene Flow in 3D Point Cloudscited by 35
  6. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  7. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  8. 2019Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenescited by 27
  9. 2020PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Cloudscited by 20
  10. 2019LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Imagescited by 12

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 1.

7 papers.

  1. 2024SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAMcited by 41
  2. 2023Self-Supervised 3D Scene Flow Estimation Guided by Superpointscited by 24
  3. 20243DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labellingcited by 14
  4. 2023DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Modelcited by 11
  5. 2025DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidancecited by 4
  6. 2023RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimationcited by 3
  7. 2024NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolationcited by 3