Neural Eulerian Scene Flow Fields
Kyle Vedder, Neehar Peri, Ishan Khatri, Siyi Li, Eric Eaton, Mehmet Kemal Kocamaz, Yue Wang, Zhiding Yu, Deva Ramanan, Joachim Pehserl
Abstract
2 NVIDIA 3 Carnegie Mellon University (a) Small object motion extraction... (b) ...in diverse, dynamic scenes... (c) ...with emergent 3D point tracking behavior! Figure 1 : EulerFlow is able to capture the motion of small, fast moving objects with few lidar points, such a bird flying in front of an autonomous vehicle (Figure 1a ). EulerFlow's flexibility allows it to estimate scene flow for fast-moving table top objects without additional hyperparameter tuning (Figure 1b ). EulerFlow's ODE estimate exhibits emergent 3D point tracking behavior without explicit long-horizon supervision (Figure 1c ). Note that point clouds are shown in color for visualization purposes only; RGB is not used during optimization.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers8
- Any4D: Unified Feed-Forward Metric 4D ReconstructionJay Karhade, Nikhil Varma Keetha, Yuchen Zhang, Tanisha Gupta et al.CVPR 2026 · 35 citations
- Flux4D: Flow-based Unsupervised 4D ReconstructionJingkang Wang, Henry Che, Yun Chen, Ze Yang et al.NeurIPS 2025 · 10 citations
- DeltaFlow: An Efficient Multi-frame Scene Flow Estimation MethodQingwen Zhang, Xiaomeng Zhu, Yushan Zhang, Yixi Cai et al.NeurIPS 2025 · 8 citations
- E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit RegularizationWenpu Li, Bangyan Liao, Yi Zhou, Qi Xu et al.NeurIPS 2025 · 4 citations
- Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow EstimationJingyun Fu, Zhiyu Xiang, Na ZhaoICML 2026
Builds on12
- Liquid Time-constant NetworksRamin M. Hasani, Mathias Lechner, Alexander Amini, Daniela Rus et al.AAAI 2021 · 399 citations
- Neural Scene Flow PriorXueqian Li, Jhony Kaesemodel Pontes, Simon LuceyNeurIPS 2021 · 136 citations
- Fast Neural Scene FlowXueqian Li, Jianqiao Zheng, Francesco Ferroni, Jhony Kaesemodel Pontes et al.ICCV 2023 · 41 citations
- Forecasting from LiDAR via Future Object DetectionNeehar Peri, Jonathon Luiten, Mengtian Li, Aljosa Osep et al.CVPR 2022 · 33 citations
- Neural Prior for Trajectory EstimationChaoyang Wang, Xueqian Li, Jhony Kaesemodel Pontes, Simon LuceyCVPR 2022 · 19 citations
Related papers
- 3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-LabellingChaokang Jiang, Guangming Wang, Jiuming Liu, Hesheng Wang et al.CVPR 2024
- SCOOP: Self-Supervised Correspondence and Optimization-Based Scene FlowItai Lang, Dror Aiger, Forrester Cole, Shai Avidan et al.CVPR 2023
- SLIM: Self-Supervised LiDAR Scene Flow and Motion SegmentationStefan Andreas Baur, David Josef Emmerichs, Frank Moosmann, Peter Pinggera et al.ICCV 2021 · 110 citations
- MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View MapsPengxiang Wu, Siheng Chen, Dimitris N. MetaxasCVPR 2020
- SeMoLi: What Moves Together Belongs TogetherJenny Seidenschwarz, Aljosa Osep, Francesco Ferroni, Simon Lucey et al.CVPR 2024 · 3 citations
