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 101–110 of 741 papers

TitleStatusHype
Explicit Motion Disentangling for Efficient Optical Flow EstimationCode1
Deep Blind Video Super-resolutionCode1
CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial OdometryCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit AllocationCode1
Channel Attention Is All You Need for Video Frame InterpolationCode1
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion PredictionCode1
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo VideosCode1
Instance-wise Depth and Motion Learning from Monocular VideosCode1
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion EstimationCode1
Show:102550
← PrevPage 11 of 75Next →

No leaderboard results yet.