Motion Estimation
206 papers with code • 0 benchmarks • 9 datasets
Motion Estimation is used to determine the block-wise or pixel-wise motion vectors between two frames.
Benchmarks
These leaderboards are used to track progress in Motion Estimation
Libraries
Use these libraries to find Motion Estimation models and implementationsDatasets
Latest papers
PeLiCal: Targetless Extrinsic Calibration via Penetrating Lines for RGB-D Cameras with Limited Co-visibility
The extrinsic calibration of these systems introduces additional complexities.
A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals
One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities.
CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization
This paper considers the problem of rotational motion estimation using event cameras.
3D Semantic Segmentation-Driven Representations for 3D Object Detection
In autonomous driving, 3D detection provides more precise information to downstream tasks, including path planning and motion estimation, compared to 2D detection.
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation
In this study we focus on the new task of multi-hypothesis motion estimation.
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV
Self-supervised learning is the key to unlocking generic computer vision systems.
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation
Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community.
Event-Based Visual Odometry on Non-Holonomic Ground Vehicles
Despite the promise of superior performance under challenging conditions, event-based motion estimation remains a hard problem owing to the difficulty of extracting and tracking stable features from event streams.
Refining Pre-Trained Motion Models
In the first stage, we use the pre-trained model to estimate motion in a video, and then select the subset of motion estimates which we can verify with cycle-consistency.
Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry
This paper overviews different pose representations and metric functions in visual odometry (VO) networks.