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 301–350 of 2184 papers

TitleStatusHype
Cascaded Deep Video Deblurring Using Temporal Sharpness PriorCode1
Event Collapse in Contrast Maximization FrameworksCode1
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow EstimationCode1
Explicit Motion Disentangling for Efficient Optical Flow EstimationCode1
Exploiting temporal and depth information for multi-frame face anti-spoofingCode1
Exploring Spatial-Temporal Features for Deepfake Detection and LocalizationCode1
Texture-guided Saliency Distilling for Unsupervised Salient Object DetectionCode1
FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed ModelCode1
FastAno: Fast Anomaly Detection via Spatio-temporal Patch TransformationCode1
Comparing Correspondences: Video Prediction with Correspondence-wise LossesCode1
Diffeomorphic Particle Image VelocimetryCode1
Creating Artificial Modalities to Solve RGB LivenessCode1
FLAVR: Flow-Agnostic Video Representations for Fast Frame InterpolationCode1
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo MatchingCode1
DF-VO: What Should Be Learnt for Visual Odometry?Code1
DIP: Deep Inverse Patchmatch for High-Resolution Optical FlowCode1
E-RAFT: Dense Optical Flow from Event CamerasCode1
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent TransformerCode1
Dense Continuous-Time Optical Flow from Events and FramesCode1
AnimeRun: 2D Animation Visual Correspondence from Open Source 3D MoviesCode1
Conditional Object-Centric Learning from VideoCode1
CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow EstimationCode1
Future Frame Prediction for Anomaly Detection – A New BaselineCode1
GAFlow: Incorporating Gaussian Attention into Optical FlowCode1
GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion EstimatesCode1
Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time TrainingCode1
AccFlow: Backward Accumulation for Long-Range Optical FlowCode1
Volterra Neural Networks (VNNs)Code1
Conquering the cnn over-parameterization dilemma: A volterra filtering approach for action recognitionCode1
Delving into Crispness: Guided Label Refinement for Crisp Edge DetectionCode1
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion ModelsCode1
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow LearningCode1
Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source LocalizationCode1
Hidden Two-Stream Convolutional Networks for Action RecognitionCode1
Unified Domain Adaptive Semantic SegmentationCode1
High-Resolution Optical Flow from 1D Attention and CorrelationCode1
A Simple Detector with Frame Dynamics is a Strong TrackerCode1
Deep Video Super-Resolution using HR Optical Flow EstimationCode1
Animation from Blur: Multi-modal Blur Decomposition with Motion GuidanceCode1
Deficiency-Aware Masked Transformer for Video InpaintingCode1
Inertia-Guided Flow Completion and Style Fusion for Video InpaintingCode1
BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical FlowCode1
Internal Video Inpainting by Implicit Long-range PropagationCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Is Appearance Free Action Recognition Possible?Code1
Deep Video Matting via Spatio-Temporal Alignment and AggregationCode1
DEFLOW: Self-supervised 3D Motion Estimation of Debris FlowCode1
Counting People by Estimating People FlowsCode1
L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B ImageryCode1
Depth-Cooperated Trimodal Network for Video Salient Object DetectionCode1
Show:102550
← PrevPage 7 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