SOTAVerified

Scene Flow Estimation

Optical flow is a two-dimensional motion field in the image plane. It is the projection of the three-dimensional motion of the world. If the world is completely non-rigid, the motions of the points in the scene may all be indepen- dent of each other. One representation of the scene motion is therefore a dense three-dimensional vector field defined for every point on every surface in the scene. By analogy with optical flow, we refer to this three-dimensional motion field as scene flow.

Source: Vedula, Sundar, et al. "Three-dimensional scene flow." IEEE transactions on pattern analysis and machine intelligence 27.3 (2005): 475-480. pdf

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 152 papers

TitleStatusHype
GMSF: Global Matching Scene FlowCode1
ZeroFlow: Scalable Scene Flow via DistillationCode1
Self-Supervised 3D Scene Flow Estimation Guided by SuperpointsCode1
Fast Neural Scene FlowCode1
DEFLOW: Self-supervised 3D Motion Estimation of Debris FlowCode1
Re-Evaluating LiDAR Scene Flow for Autonomous Driving—0
Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR FusionCode2
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point CloudsCode0
Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and StereoCode1
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal SupervisionCode1
PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds—0
IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow EstimationCode0
Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow EstimationCode0
EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity—0
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene FlowCode1
3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion—0
SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and SelectionCode1
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance—0
PointConvFormer: Revenge of the Point-based Convolution—0
What Matters for 3D Scene Flow NetworkCode1
Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow EstimationCode1
M-FUSE: Multi-frame Fusion for Scene Flow EstimationCode1
Unsupervised Learning of 3D Scene Flow from Monocular CameraCode0
RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds—0
UnPWC-SVDLO: Multi-SVD on PointPWC for Unsupervised Lidar Odometry—0
RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer—0
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds—0
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point CloudsCode1
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions—0
DetFlowTrack: 3D Multi-object Tracking based on Simultaneous Optimization of Object Detection and Scene Flow Estimation—0
Self-Supervised Scene Flow Estimation with 4-D Automotive RadarCode1
Dual Task Learning by Leveraging Both Dense Correspondence and Mis-Correspondence for Robust Change Detection With Imperfect MatchesCode1
RCP: Recurrent Closest Point for Point CloudCode0
Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation—0
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular ImagesCode1
CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow EstimationCode1
Learning Scene Dynamics from Point Cloud Sequences—0
Neural Scene Flow PriorCode1
Accurate Point Cloud Registration with Robust Optimal TransportCode1
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation—0
Residual 3D Scene Flow Learning with Context-Aware Feature Extraction—0
Neighborhood Normalization for Robust Geometric Feature LearningCode1
Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids—0
Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk—0
SCTN: Sparse Convolution-Transformer Network for Scene Flow EstimationCode1
Self-Supervised Multi-Frame Monocular Scene FlowCode1
Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point CloudsCode0
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point CloudsCode1
Scalable Scene Flow from Point Clouds in the Real WorldCode1
Show:102550
← PrevPage 2 of 4Next →
All datasetsArgoverse 2SpringKITTI 2015 Scene Flow TestKITTI 2015 Scene Flow Training

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FastNSFEPE 3-Way0.11—Unverified
2FastFlow3DEPE 3-Way0.06—Unverified
3NSFPEPE 3-Way0.06—Unverified
4ZeroFlow 5x XLEPE 3-Way0.05—Unverified
5SeFlowEPE 3-Way0.05—Unverified
6TrackFlowEPE 3-Way0.05—Unverified
7DeFlowEPE 3-Way0.03—Unverified
#ModelMetricClaimedVerifiedStatus
1CamLiFlow (K)1px total85.31—Unverified
2RAFT-3D (F)1px total78.82—Unverified
3M-FUSE (K)1px total62.49—Unverified
4CamLiFlow (F)1px total50.08—Unverified
5RAFT-3D (K)1px total37.26—Unverified
6M-FUSE (F)1px total34.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Self-Mono-SFSF-all49.54—Unverified
2Multi-Mono-SFSF-all44.04—Unverified
3PWOC-3DSF-all15.69—Unverified
4CamLiRAFTSF-all4.26—Unverified
#ModelMetricClaimedVerifiedStatus
1Self-Mono-SFD1-all31.25—Unverified
2Multi-Mono-SFD1-all27.33—Unverified
3EPCD1-all26.81—Unverified
4EPC++D1-all23.84—Unverified