SOTAVerified

Optical Flow Estimation

Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.

Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.

Further readings:

Definition source: Devon: Deformable Volume Network for Learning Optical Flow

Image credit: Optical Flow Estimation

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–400 of 2184 papers

TitleStatusHype
VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good EnoughCode1
VOLDOR: Visual Odometry from Log-logistic Dense Optical flow ResidualsCode1
Progressive Temporal Feature Alignment Network for Video InpaintingCode1
Learning optical flow from still imagesCode1
Deep Animation Video Interpolation in the WildCode1
Learning to Estimate Hidden Motions with Global Motion AggregationCode1
Learning Optical Flow from a Few MatchesCode1
Deep Two-View Structure-from-Motion RevisitedCode1
XVFI: eXtreme Video Frame InterpolationCode1
Broaden Your Views for Self-Supervised Video LearningCode1
HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark DatasetCode1
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow LearningCode1
Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature AggregationCode1
COTR: Correspondence Transformer for Matching Across ImagesCode1
Efficient Regional Memory Network for Video Object SegmentationCode1
Model-free Vehicle Tracking and State Estimation in Point Cloud SequencesCode1
FastFlowNet: A Lightweight Network for Fast Optical Flow EstimationCode1
Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient MaskCode1
DF-VO: What Should Be Learnt for Visual Odometry?Code1
Normalized Convolution Upsampling for Refined Optical Flow EstimationCode1
Hybrid Neural Fusion for Full-frame Video StabilizationCode1
Frame Difference-Based Temporal Loss for Video StylizationCode1
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection ConsistencyCode1
Deep Online Fused Video StabilizationCode1
Deep Burst Super-ResolutionCode1
Supervision by Registration and Triangulation for Landmark DetectionCode1
FlowReg: Fast Deformable Unsupervised Medical Image Registration using Optical FlowCode1
Object Tracking by Detection with Visual and Motion CuesCode1
Reinforcement Learning with Latent FlowCode1
Learning Accurate Dense Correspondences and When to Trust ThemCode1
Separable Flow: Learning Motion Cost Volumes for Optical Flow EstimationCode1
FLAVR: Flow-Agnostic Video Representations for Fast Frame InterpolationCode1
DS-Net: Dynamic Spatiotemporal Network for Video Salient Object DetectionCode1
Fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcastingCode1
Counting People by Estimating People FlowsCode1
RAFT-3D: Scene Flow using Rigid-Motion EmbeddingsCode1
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow LearningCode1
Deep Multi-view Depth Estimation with Predicted UncertaintyCode1
RIFE: Real-Time Intermediate Flow Estimation for Video Frame InterpolationCode1
TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency LossCode1
Mutual Modality Learning for Video Action ClassificationCode1
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow EstimationCode1
Blind Video Temporal Consistency via Deep Video PriorCode1
Self-supervised Co-training for Video Representation LearningCode1
Local-Global Fusion Network for Video Super-ResolutionCode1
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural NetworkCode1
When Deep Learning Meets Digital Image CorrelationCode1
Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video EventsCode1
DTVNet: Dynamic Time-lapse Video Generation via Single Still ImageCode1
Learning to See Through Obstructions with Layered DecompositionCode1
Show:102550
← PrevPage 8 of 44Next →
All datasetsSintel-cleanSintel-finalKITTI 2015 (train)KITTI 2015KITTI 2012SpringSintel Clean unsupervisedSintel Final unsupervisedKITTI 2015 unsupervisedKITTI 2012 unsupervised

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SpynetAverage End-Point Error6.64—Unverified
2FastFlowNet-ftAverage End-Point Error4.89—Unverified
3UnrolledCostAverage End-Point Error4.69—Unverified
4LiteFlowNet-ftAverage End-Point Error4.54—Unverified
5FlowNet2Average End-Point Error3.96—Unverified
6IRR-PWCAverage End-Point Error3.84—Unverified
7SelFlowAverage End-Point Error3.74—Unverified
8FDFlowNet-ftAverage End-Point Error3.71—Unverified
9ScopeFlowAverage End-Point Error3.59—Unverified
10LiteFlowNet2-ftAverage End-Point Error3.48—Unverified
#ModelMetricClaimedVerifiedStatus
1SpynetAverage End-Point Error8.36—Unverified
2FastFlowNet-ftAverage End-Point Error6.08—Unverified
3UnrolledCostAverage End-Point Error5.8—Unverified
4MR-FlowAverage End-Point Error5.38—Unverified
5LiteFlowNet-ftAverage End-Point Error5.38—Unverified
6FDFlowNet-ftAverage End-Point Error5.11—Unverified
7LiteFlowNet2-ftAverage End-Point Error4.69—Unverified
8IRR-PWCAverage End-Point Error4.58—Unverified
9LiteFlowNet3-SAverage End-Point Error4.53—Unverified
10ContinualFlow + ftAverage End-Point Error4.52—Unverified
#ModelMetricClaimedVerifiedStatus
1PWC-NetF1-all33.7—Unverified
2FastFlowNetF1-all33.1—Unverified
3FlowNet2F1-all30—Unverified
4VCNF1-all25.1—Unverified
5HD3F1-all24—Unverified
6MaskFlowNetF1-all23.1—Unverified
7SCVF1-all19.3—Unverified
8RAPIDFlowF1-all17.7—Unverified
9CRAFTF1-all17.5—Unverified
10RAFTF1-all17.4—Unverified
#ModelMetricClaimedVerifiedStatus
1FastFlowNet-ftFl-all11.22—Unverified
2UnrolledCostFl-all10.81—Unverified
3LiteFlowNet-ftFl-all9.38—Unverified
4SelFlowFl-all8.42—Unverified
5IRR-PWCFl-all7.65—Unverified
6LiteFlowNet2-ftFl-all7.62—Unverified
7LiteFlowNet3Fl-all7.34—Unverified
8LiteFlowNet3-SFl-all7.22—Unverified
9MaskFlownet-SFl-all6.81—Unverified
10RAPIDFlowFl-all6.12—Unverified
#ModelMetricClaimedVerifiedStatus
1FastFlowNet-ftAverage End-Point Error1.8—Unverified
2LiteFlowNet-ftAverage End-Point Error1.6—Unverified
3IRR-PWCAverage End-Point Error1.6—Unverified
4SelFlowAverage End-Point Error1.5—Unverified
5FDFlowNet-ftAverage End-Point Error1.5—Unverified
6PWC-Net + ft - axXivAverage End-Point Error1.5—Unverified
7LiteFlowNet2-ftAverage End-Point Error1.4—Unverified
8LiteFlowNet3-SAverage End-Point Error1.3—Unverified
9LiteFlowNet3Average End-Point Error1.3—Unverified
10MaskFlownetAverage End-Point Error1.1—Unverified
#ModelMetricClaimedVerifiedStatus
1PWCNet1px total82.27—Unverified
2SPyNet1px total29.96—Unverified
3GMFlow1px total10.36—Unverified
4GMA1px total7.07—Unverified
5RAFT1px total6.79—Unverified
6FlowNet21px total6.71—Unverified
7FlowFormer1px total6.51—Unverified
8MS-RAFT+1px total5.72—Unverified
9RPKNet1px total4.81—Unverified
10DPFlow1px total3.44—Unverified
#ModelMetricClaimedVerifiedStatus
1UFlowAverage End-Point Error5.21—Unverified
2MDFlow-FastAverage End-Point Error4.73—Unverified
3UpFlowAverage End-Point Error4.68—Unverified
4ARFlow-MVAverage End-Point Error4.49—Unverified
5MDFlowAverage End-Point Error4.16—Unverified
#ModelMetricClaimedVerifiedStatus
1UFlowAverage End-Point Error6.5—Unverified
2MDFlow-FastAverage End-Point Error5.99—Unverified
3ARFlow-MVAverage End-Point Error5.67—Unverified
4MDFlowAverage End-Point Error5.46—Unverified
5UpFlowAverage End-Point Error5.32—Unverified
#ModelMetricClaimedVerifiedStatus
1ARFlow-MVFl-all11.79—Unverified
2MDFlow-FastFl-all11.43—Unverified
3UpFlowFl-all9.38—Unverified
4MDFlowFl-all8.91—Unverified
#ModelMetricClaimedVerifiedStatus
1ARFlow-MVAverage End-Point Error1.5—Unverified
2UpFlowAverage End-Point Error1.4—Unverified