mlsanityData to 14 Oct 2026

EgoFlowNet: Non-Rigid Scene Flow from Point Clouds with Ego-Motion Support

arXiv 2407.02920 ↗First posted 3 Jul 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable to clustering robustness. In this paper, we propose our EgoFlowNet - a point-level scene flow estimation network trained in a weakly-supervised manner and without object-based abstraction. Our approach predicts a binary segmentation mask that implicitly drives two parallel branches for ego-motion and scene flow. Unlike previous methods, we provide both branches with all input points and carefully integrate the binary mask into the feature extraction and losses. We also use a shared cost volume with local refinement that is updated at multiple scales without explicit clustering or rigidity assumptions. On realistic KITTI scenes, we show that our EgoFlowNet performs better than state-of-the-art methods in the presence of ground surface points.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

33 of 50 references.

References · 33

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  3. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  4. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  5. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  6. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  7. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  8. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  9. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
  10. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 109
  11. 2019Just Go with the Flow: Self-Supervised Scene Flow Estimationcited by 98
  12. 2020PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Cloudscited by 74
21 more
  1. 2020FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimationcited by 71
  2. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  3. 2019PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalcited by 68
  4. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  5. 2019Deep Rigid Instance Scene Flowcited by 54
  6. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 48
  7. 2018Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstructioncited by 44
  8. 2020Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motioncited by 41
  9. 2021Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walkcited by 39
  10. 2019SENSE: a Shared Encoder Network for Scene-flow Estimationcited by 38
  11. 2022Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimationcited by 38
  12. 2021HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embeddingcited by 36
  13. 2020Hierarchical Attention Learning of Scene Flow in 3D Point Cloudscited by 35
  14. 2022What Matters for 3D Scene Flow Networkcited by 31
  15. 2019PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimationcited by 20
  16. 2018Motion-based Object Segmentation based on Dense RGB-D Scene Flowcited by 18
  17. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  18. 2019SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimationcited by 6
  19. 2020Consistency Guided Scene Flow Estimationcited by 5
  20. 2022RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Cloudscited by 5
  21. 2022Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistancecited by 2

Built on by

Not cited yet.