Scene Flow Estimation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 81 papers with code (152 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Scalable Scene Flow from Point Clouds in the Real World
  1 Mar 2021 5 repositories listed
  In this work, we introduce a new large-scale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is ∼1, 000× larger than previous real-world datasets in terms of the number of…
• DeFlow: Decoder of Scene Flow Network in Autonomous Driving
  29 Jan 2024 4 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving.
• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
  7 Dec 2015 3 repositories listed
  By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
• SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving
  1 Jul 2024 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans.
• Let-It-Flow: Simultaneous Optimization of 3D Flow and Object Clustering
  12 Apr 2024 2 repositories listed
  We identified the structural constraints and the use of large and strict rigid clusters as the main pitfall of the current approaches and we propose a novel clustering approach that allows for combination of overlapping…
• milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
  29 Jun 2023 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  In this work, we propose milliFlow, a novel deep learning approach to estimate scene flow as complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting…
• Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo
  3 Mar 2023 2 repositories listed Syntology ran 4 of 6 samples · 2 unverified · 4 pointer-only (licence)
  While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation…
• 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
  2 May 2022 2 repositories listed Syntology ran 0 of 16 samples · 16 unverified
  Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head.
• Self-Supervised Scene Flow Estimation with 4-D Automotive Radar
  2 Mar 2022 2 repositories listed Syntology ran 2 of 12 samples · 10 unverified
  Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy.
• Accurate Point Cloud Registration with Robust Optimal Transport
  1 Nov 2021 2 repositories listed
  Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric…
• PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
  27 Nov 2019 2 repositories listed Syntology ran 2 of 18 samples · 16 unverified
  We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.
• MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
  21 Oct 2019 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Understanding dynamic 3D environment is crucial for robotic agents and many other applications.
• HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
  12 Jun 2019 2 repositories listed
  We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.
• KDMOS:Knowledge Distillation for Motion Segmentation
  17 Jun 2025 1 repository listed
  To handle the severe imbalance between moving and non-moving classes, we decouple them and apply tailored distillation strategies, allowing the teacher model to better learn key motion-related features.
• VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow
  28 Mar 2025 1 repository listed
  Scene flow estimation aims to recover per-point motion from two adjacent LiDAR scans.
• MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation
  24 Feb 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  In this paper, we propose MambaFlow, a novel scene flow estimation network with a mamba-based decoder.
• SSF: Sparse Long-Range Scene Flow for Autonomous Driving
  29 Jan 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  To address this, we propose a sparse feature fusion scheme, that augments the feature maps with virtual voxels at missing locations.
• STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
  31 Dec 2024 1 repository listed
  We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations.
• FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
  25 Oct 2024 1 repository listed
  Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure.
• ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
  16 Sep 2024 1 repository listed
  Unlike previous methods, ScaleFlow++ integrates optical flow and MID estimation into a unified architecture, estimating optical flow and MID end-to-end based on feature matching.
• ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
  13 Jul 2024 1 repository listed
  Unlike previous methods, ScaleFlow++ integrates optical flow and MID estimation into a unified architecture, estimating optical flow and MID end-to-end based on feature matching.
• Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
  10 Jul 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information.
• SceneTracker: Long-term Scene Flow Estimation Network
  29 Mar 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that…
• Fast Kernel Scene Flow
  9 Mar 2024 1 repository listed
  In contrast to current state-of-the-art methods, such as NSFP [25], which employ deep implicit neural functions for modeling scene flow, we present a novel approach that utilizes classical kernel representations.
• DiffSF: Diffusion Models for Scene Flow Estimation
  8 Mar 2024 1 repository listed Syntology ran 10 of 11 samples · 1 unverified · 11 pointer-only (licence)
  Aiming at improving accuracy while additionally providing an estimate for uncertainty, we propose DiffSF that combines transformer-based scene flow estimation with denoising diffusion models.
• 3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
  28 Feb 2024 1 repository listed Syntology ran 9 of 10 samples · 1 unverified
  We present a novel approach from the perspective of auto-labelling, aiming to generate a large number of 3D scene flow pseudo labels for real-world LiDAR point clouds.
• ICP-Flow: LiDAR Scene Flow Estimation with ICP
  27 Feb 2024 1 repository listed Syntology ran 8 of 9 samples · 1 unverified
  We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations.
• FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units
  23 Jan 2024 1 repository listed
  In this paper, we introduce FedRSU, an innovative federated learning framework for self-supervised scene flow estimation.
• DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement
  1 Jan 2024 1 repository listed
  Furthermore we also develop an uncertainty estimation module within diffusion to evaluate the reliability of estimated scene flow.
• Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic Consistency
  12 Dec 2023 1 repository listed
  Learning without supervision how to predict 3D scene flows from point clouds is essential to many perception systems.

Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.