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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 141–150 of 741 papers

TitleStatusHype
Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal CorrespondenceCode1
DeepFaceFlow: In-the-wild Dense 3D Facial Motion EstimationCode1
Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB VideoCode1
Deep Orientation Uncertainty Learning based on a Bingham LossCode1
Channel Attention Is All You Need for Video Frame InterpolationCode1
Deep Blind Video Super-resolutionCode1
DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular VideosCode1
MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic NavigationCode1
Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D GeometryCode1
Self-Supervised Linear Motion DeblurringCode1
Show:102550
← PrevPage 15 of 75Next →

No leaderboard results yet.