Browse > Computer Vision > Motion Estimation

Motion Estimation

53 papers with code · Computer Vision

Leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Visual-Inertial Mapping with Non-Linear Factor Recovery

13 Apr 2019VladyslavUsenko/basalt-mirror

We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO.

MOTION ESTIMATION

The Double Sphere Camera Model

24 Jul 2018VladyslavUsenko/basalt-mirror

We evaluate the model using a calibration dataset with several different lenses and compare the models using the metrics that are relevant for Visual Odometry, i. e., reprojection error, as well as computation time for projection and unprojection functions and their Jacobians.

3D RECONSTRUCTION AUTONOMOUS DRIVING CALIBRATION MOTION ESTIMATION VISUAL ODOMETRY

CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction

1 Oct 2018yan99033/CNN-SVO

Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms.

DEPTH ESTIMATION MOTION ESTIMATION SIMULTANEOUS LOCALIZATION AND MAPPING VISUAL ODOMETRY

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

CVPR 2018 yhjo09/VSR-DUF

We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation.

DATA AUGMENTATION MOTION COMPENSATION MOTION ESTIMATION VIDEO SUPER-RESOLUTION

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

25 Feb 2019hlzz/DeepMatchVO

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM).

MOTION ESTIMATION SELF-SUPERVISED LEARNING SIMULTANEOUS LOCALIZATION AND MAPPING VISUAL ODOMETRY

Taking a Deeper Look at the Inverse Compositional Algorithm

CVPR 2019 lvzhaoyang/DeeperInverseCompositionalAlgorithm

In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment.

MOTION ESTIMATION

Self-Supervised 3D Keypoint Learning for Ego-motion Estimation

7 Dec 2019TRI-ML/KP3D

Generating reliable illumination and viewpoint invariant keypoints is critical for feature-based SLAM and SfM.

KEYPOINT DETECTION MOTION ESTIMATION VISUAL ODOMETRY

FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation

1 Jul 2019m-tassano/fastdvdnet

In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture.

DENOISING MOTION COMPENSATION MOTION ESTIMATION VIDEO DENOISING

Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos

8 Oct 2018baidu-research/UnDepthflow

Then the whole scene is decomposed into moving foreground and static background by compar- ing the estimated optical flow and rigid flow derived from the depth and ego-motion.

MOTION ESTIMATION OPTICAL FLOW ESTIMATION