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 101–150 of 152 papers

TitleStatusHype
Weakly Supervised Learning of Rigid 3D Scene FlowCode1
Optical flow and scene flow estimation: A survey—0
Learning to Segment Rigid Motions from Two FramesCode1
Warping of Radar Data into Camera Image for Cross-Modal Supervision in Automotive Applications—0
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association—0
PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point CloudsCode1
RAFT-3D: Scene Flow using Rigid-Motion EmbeddingsCode1
Occlusion Guided Scene Flow Estimation on 3D Point CloudsCode0
FlowStep3D: Model Unrolling for Self-Supervised Scene Flow EstimationCode0
EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation—0
Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation—0
Adversarial Self-Supervised Scene Flow EstimationCode1
Hierarchical Attention Learning of Scene Flow in 3D Point Clouds—0
DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARCode0
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow EstimationCode1
FLOT: Scene Flow on Point Clouds Guided by Optimal TransportCode1
LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow EstimationCode1
ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching—0
Consistency Guided Scene Flow Estimation—0
AANet: Adaptive Aggregation Network for Efficient Stereo MatchingCode1
Self-Supervised Monocular Scene Flow EstimationCode1
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation—0
Just Go with the Flow: Self-Supervised Scene Flow EstimationCode0
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point CloudsCode1
LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images—0
SENSE: a Shared Encoder Network for Scene-flow EstimationCode0
MeteorNet: Deep Learning on Dynamic 3D Point Cloud SequencesCode1
Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation—0
Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes—0
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point CloudsCode1
A Conditional Adversarial Network for Scene Flow EstimationCode0
Deep Rigid Instance Scene Flow—0
Self-Supervised Flow Estimation using Geometric Regularization with Applications to Camera Image and Grid Map Sequences—0
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow EstimationCode0
SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation—0
Deep learning based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography—0
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic UnderstandingCode0
Dense Scene Flow from Stereo Disparity and Optical Flow—0
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow EstimationCode0
SceneEDNet: A Deep Learning Approach for Scene Flow EstimationCode0
Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding—0
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds—0
4D Temporally Coherent Light-field Video—0
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field EstimationCode0
Combining Stereo Disparity and Optical Flow for Basic Scene Flow—0
Multiframe Scene Flow with Piecewise Rigid Motion—0
Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?—0
Simultaneous Stereo Video Deblurring and Scene Flow Estimation—0
Scene Flow Estimation: A Survey—0
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow EstimationCode1
Show:102550
← PrevPage 3 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