SOTAVerified

Motion Estimation

Motion Estimation is used to determine the block-wise or pixel-wise motion vectors between two frames.

Source: MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement

Papers

Showing 101150 of 741 papers

TitleStatusHype
Motion Vector Extrapolation for Video Object DetectionCode1
iSLAM: Imperative SLAMCode1
DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular VideosCode1
On the Benefits of Visual Stabilization for Frame- and Event-based PerceptionCode1
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo VideosCode1
Channel Attention Is All You Need for Video Frame InterpolationCode1
Digging Into Self-Supervised Monocular Depth EstimationCode1
Learning-based Localizability Estimation for Robust LiDAR LocalizationCode1
Non-linear Motion Estimation for Video Frame Interpolation using Space-time ConvolutionsCode1
Spatio-Temporal State Space Model For Efficient Event-Based Optical FlowCode1
4DComplete: Non-Rigid Motion Estimation Beyond the Observable SurfaceCode1
CNN-based Ego-Motion Estimation for Fast MAV ManeuversCode1
Learning to Estimate and Refine Fluid Motion with Physical DynamicsCode1
Live Stream Temporally Embedded 3D Human Body Pose and Shape EstimationCode1
Oflib: Facilitating Operations with and on Optical Flow Fields in PythonCode1
Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape ImagesCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
Towards Anytime Optical Flow Estimation with Event CamerasCode1
4D Myocardium Reconstruction with Decoupled Motion and Shape ModelCode1
Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth EstimationCode1
Micro Expression Generation with Thin-plate Spline Motion Model and Face ParsingCode1
Minimum Latency Deep Online Video StabilizationCode1
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan SynchronizationCode1
Motion-adaptive Separable Collaborative Filters for Blind Motion DeblurringCode1
Motion Correction and Volumetric Reconstruction for Fetal Functional Magnetic Resonance Imaging DataCode1
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion EstimationCode1
Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset FeatureCode1
Deep Orientation Uncertainty Learning based on a Bingham LossCode1
DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention NetworksCode1
Efficient Feature Extraction for High-resolution Video Frame InterpolationCode1
DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place RecognitionCode1
Deep Shutter Unrolling NetworkCode1
Multiple Video Frame Interpolation via Enhanced Deformable Separable ConvolutionCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
DeepMesh: Mesh-based Cardiac Motion Tracking using Deep LearningCode1
CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial OdometryCode1
DEFLOW: Self-supervised 3D Motion Estimation of Debris FlowCode1
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion PredictionCode1
A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization FrameworkCode1
Explicit Motion Disentangling for Efficient Optical Flow EstimationCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
Distracting Downpour: Adversarial Weather Attacks for Motion EstimationCode1
PARIS: Part-level Reconstruction and Motion Analysis for Articulated ObjectsCode1
Deep Blind Video Super-resolutionCode1
Asymmetric Bilateral Motion Estimation for Video Frame InterpolationCode1
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised TrainingCode1
DeepFaceFlow: In-the-wild Dense 3D Facial Motion EstimationCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Restoration of Non-rigidly Distorted Underwater Images using a Combination of Compressive Sensing and Local Polynomial Image RepresentationsCode1
Self-Supervised Pillar Motion Learning for Autonomous DrivingCode1
Show:102550
← PrevPage 3 of 15Next →

No leaderboard results yet.