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
Neural Scene Flow PriorCode1
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point CloudsCode1
Neighborhood Normalization for Robust Geometric Feature LearningCode1
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
Multi-Body Neural Scene FlowCode1
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow EstimationCode1
Adversarial Self-Supervised Scene Flow EstimationCode1
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular ImagesCode1
Weakly Supervised Learning of Rigid 3D Scene FlowCode1
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion SensingCode1
Learning to Segment Rigid Motions from Two FramesCode1
Let-It-Flow: Simultaneous Optimization of 3D Flow and Object ClusteringCode1
M-FUSE: Multi-frame Fusion for Scene Flow EstimationCode1
SceneEDNet: A Deep Learning Approach for Scene Flow EstimationCode0
A Conditional Adversarial Network for Scene Flow EstimationCode0
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARCode0
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic UnderstandingCode0
Exploiting Implicit Rigidity Constraints via Weight-Sharing Aggregation for Scene Flow Estimation from Point CloudsCode0
FedRSU: Federated Learning for Scene Flow Estimation on Roadside UnitsCode0
FlowStep3D: Model Unrolling for Self-Supervised Scene Flow EstimationCode0
IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow EstimationCode0
Just Go with the Flow: Self-Supervised Scene Flow EstimationCode0
KDMOS:Knowledge Distillation for Motion SegmentationCode0
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field EstimationCode0
DirDist: A Metric for Comparing 3D Shapes Using Directional Distance FieldsCode0
Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow EstimationCode0
Occlusion Guided Scene Flow Estimation on 3D Point CloudsCode0
Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point CloudsCode0
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow EstimationCode0
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow EstimationCode0
RCP: Recurrent Closest Point for Point CloudCode0
Regularizing Self-supervised 3D Scene Flows with Surface Awareness and Cyclic ConsistencyCode0
SENSE: a Shared Encoder Network for Scene-flow EstimationCode0
SSF: Sparse Long-Range Scene Flow for Autonomous DrivingCode0
Unsupervised Learning of 3D Scene Flow from Monocular CameraCode0
Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids—0
Object Scene Flow for Autonomous Vehicles—0
Zero-Shot Monocular Scene Flow Estimation in the Wild—0
Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance—0
BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events—0
OptFlow: Fast Optimization-based Scene Flow Estimation without Supervision—0
Optical flow and scene flow estimation: A survey—0
PointConvFormer: Revenge of the Point-based Convolution—0
PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds—0
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds—0
Hierarchical Attention Learning of Scene Flow in 3D Point Clouds—0
Floxels: Fast Unsupervised Voxel Based Scene Flow Estimation—0
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation—0
VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction—0
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association—0
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