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 150 of 741 papers

TitleStatusHype
Tracking Everything Everywhere All at OnceCode4
Thin-Plate Spline Motion Model for Image AnimationCode4
VRT: A Video Restoration TransformerCode3
Event-Enhanced Blurry Video Super-ResolutionCode3
TAPIR: Tracking Any Point with per-frame Initialization and temporal RefinementCode3
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D GaussiansCode2
Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor GraphsCode2
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian SplattingCode2
Castle in the Sky: Dynamic Sky Replacement and Harmonization in VideosCode2
Splat-LOAM: Gaussian Splatting LiDAR Odometry and MappingCode2
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motionCode2
MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D ReconstructionCode2
ETAP: Event-based Tracking of Any PointCode2
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy VideoCode2
IncEventGS: Pose-Free Gaussian Splatting from a Single Event CameraCode2
BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform MotionsCode2
RaTrack: Moving Object Detection and Tracking with 4D Radar Point CloudCode2
Particle Video Revisited: Tracking Through Occlusions Using Point TrajectoriesCode2
CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast MaximizationCode2
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion DynamicsCode2
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVCode2
EchoTracker: Advancing Myocardial Point Tracking in EchocardiographyCode2
SpatialScore: Towards Unified Evaluation for Multimodal Spatial UnderstandingCode2
OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D ReconstructionCode2
Decomposition Betters Tracking Everything EverywhereCode2
Enhanced Bi-directional Motion Estimation for Video Frame InterpolationCode1
A Multi-spectral Dataset for Evaluating Motion Estimation SystemsCode1
4DComplete: Non-Rigid Motion Estimation Beyond the Observable SurfaceCode1
4D Myocardium Reconstruction with Decoupled Motion and Shape ModelCode1
DeepFaceFlow: In-the-wild Dense 3D Facial Motion EstimationCode1
Deep Blind Video Super-resolutionCode1
Entropy Minimisation Framework for Event-based Vision Model EstimationCode1
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion PredictionCode1
CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial OdometryCode1
EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted DevicesCode1
CNN-based Ego-Motion Estimation for Fast MAV ManeuversCode1
DeepMesh: Mesh-based Cardiac Motion Tracking using Deep LearningCode1
EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised TrainingCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence LossCode1
SeSame: Simple, Easy 3D Object Detection with Point-Wise SemanticsCode1
Channel Attention Is All You Need for Video Frame InterpolationCode1
AirDOS: Dynamic SLAM benefits from Articulated ObjectsCode1
BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video InterpolationCode1
Distracting Downpour: Adversarial Weather Attacks for Motion EstimationCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video InterpolationCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion EstimationCode1
Boost Video Frame Interpolation via Motion AdaptationCode1
Show:102550
← PrevPage 1 of 15Next →

No leaderboard results yet.