SfMLearner
Depth Estimator Framework
A framework for unsupervised depth and ego-motion estimation from monocular videos using deep learning
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
2k stars
77 watching
559 forks
Language: Jupyter Notebook
last commit: over 3 years ago
Linked from 1 awesome list
deep-learningdepth-predictionself-supervised-learningunsupervised-learningvisual-odometry
Related projects:
Repository | Description | Stars |
---|---|---|
| An implementation of self-supervised monocular depth estimation methods for real-time 3D reconstruction and ego-motion estimation | 1,248 |
| Pytorch implementation of unsupervised depth and ego-motion learning from video sequences | 1,022 |
| Provides software to estimate head pose from images and videos using deep learning techniques. | 1,588 |
| Real-time pose estimation for mobile devices using deep neural networks and optimized models. | 1,003 |
| This project develops software for depth estimation using defocus blur in images captured by automotive cameras. | 55 |
| A deep learning framework to estimate exposure trajectories from motion-blurred images and recover the original sharp image | 35 |
| A PyTorch-based implementation of a predictive model for human mobility patterns using attention mechanisms and recurrent neural networks. | 149 |
| A deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency. | 18 |
| A deep learning framework for multi-view fusion network-based 3D human motion capture system | 52 |
| A software framework for 3D vision and computer vision tasks using deep learning and 2D keypoints. | 431 |
| A MATLAB project that uses deep learning and stereo cameras to estimate 3D human pose from image data | 43 |
| A Matlab implementation of a 3D reconstruction algorithm using structured light depth acquisition | 70 |
| A computer vision library for detecting and tracking human presence in images and videos using convolutional neural networks. | 1,800 |
| A collection of data and tools for training algorithms to estimate dense depth in urban environments. | 497 |
| A fast and robust algorithm to segment 3D point clouds generated by Velodyne sensors into objects. | 1,212 |