anuragranj / Back2future.pytorch
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
Stars: ✭ 104
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Back2future.pytorch
Unflow
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
Stars: ✭ 239 (+129.81%)
Mutual labels: unsupervised-learning, optical-flow
Ddflow
DDFlow: Learning Optical Flow with Unlabeled Data Distillation
Stars: ✭ 101 (-2.88%)
Mutual labels: unsupervised-learning, optical-flow
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+72.12%)
Mutual labels: unsupervised-learning, optical-flow
Arflow
The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".
Stars: ✭ 134 (+28.85%)
Mutual labels: unsupervised-learning, optical-flow
back2future
Unsupervised Learning of Multi-Frame Optical Flow with Occlusions
Stars: ✭ 39 (-62.5%)
Mutual labels: optical-flow, unsupervised-learning
GuidedNet
Caffe implementation for "Guided Optical Flow Learning"
Stars: ✭ 28 (-73.08%)
Mutual labels: optical-flow, unsupervised-learning
Joint-Motion-Estimation-and-Segmentation
[MICCAI'18] Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences
Stars: ✭ 45 (-56.73%)
Mutual labels: optical-flow, unsupervised-learning
Cc
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
Stars: ✭ 348 (+234.62%)
Mutual labels: unsupervised-learning, optical-flow
PCLNet
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM.
Stars: ✭ 29 (-72.12%)
Mutual labels: optical-flow, unsupervised-learning
deepOF
TensorFlow implementation for "Guided Optical Flow Learning"
Stars: ✭ 26 (-75%)
Mutual labels: optical-flow, unsupervised-learning
Selflow
SelFlow: Self-Supervised Learning of Optical Flow
Stars: ✭ 319 (+206.73%)
Mutual labels: unsupervised-learning, optical-flow
Voxelmorph
Unsupervised Learning for Image Registration
Stars: ✭ 1,057 (+916.35%)
Mutual labels: unsupervised-learning, optical-flow
Marta Gan
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
Stars: ✭ 75 (-27.88%)
Mutual labels: unsupervised-learning
Pysad
Streaming Anomaly Detection Framework in Python (Outlier Detection for Streaming Data)
Stars: ✭ 87 (-16.35%)
Mutual labels: unsupervised-learning
Attention Based Aspect Extraction
Code for unsupervised aspect extraction, using Keras and its Backends
Stars: ✭ 75 (-27.88%)
Mutual labels: unsupervised-learning
Karateclub
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
Stars: ✭ 1,190 (+1044.23%)
Mutual labels: unsupervised-learning
Awesome Transfer Learning
Best transfer learning and domain adaptation resources (papers, tutorials, datasets, etc.)
Stars: ✭ 1,349 (+1197.12%)
Mutual labels: unsupervised-learning
Pointglr
Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds (CVPR 2020)
Stars: ✭ 86 (-17.31%)
Mutual labels: unsupervised-learning
Self Supervised Learning Overview
📜 Self-Supervised Learning from Images: Up-to-date reading list.
Stars: ✭ 73 (-29.81%)
Mutual labels: unsupervised-learning
This is a Pytorch implementation of
Janai, J., Güney, F., Ranjan, A., Black, M. and Geiger, A., Unsupervised Learning of Multi-Frame Optical Flow with Occlusions. ECCV 2018.
[Link to Paper] [Project Page] [Original Torch Code]
Requirements
- Runs and tested on Pytorch 0.3.1, it should be compatible with higher versions with little/no modifications.
- Correlation package is taken from NVIDIA/flownet2-pytorch and it can be installed using
cd correlation_package
bash make.sh
If you are using Pytorch>0.3.1, you can use correlation layer from here.
Usage
To use the model, go to your favorite python environment
from back2future import Model
model = Model(pretrained='pretrained/path_to_your_favorite_model')
There are two pretrained models in pretrained/
, that are fine tuned on Sintel and KITTI in an unsupervised way.
Refer to demo.py
for more.
Testing
To test performance on KITTI, use
python3 test_back2future.py --pretrained-flow path/to/pretrained/model --kitti-dir path/to/kitti/2015/root
Training
Please use the [original torch code] for training new models.
License
This is a reimplementation. License for the original work can be found at JJanai/back2future.
While using this code, please cite
@inproceedings{Janai2018ECCV,
title = {Unsupervised Learning of Multi-Frame Optical Flow with Occlusions },
author = {Janai, Joel and G{"u}ney, Fatma and Ranjan, Anurag and Black, Michael J. and Geiger, Andreas},
booktitle = {European Conference on Computer Vision (ECCV)},
volume = {Lecture Notes in Computer Science, vol 11220},
pages = {713--731},
publisher = {Springer, Cham},
month = sep,
year = {2018},
month_numeric = {9}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].