Maskflownet[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
UnflowUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
Df VoDepth and Flow for Visual Odometry
Liteflownet2A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Df Net[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
Opticalflow visualizationPython optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge
CloverROS-based framework and RPi image to control PX4-powered drones 🍀
Hidden Two StreamCaffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Py DenseflowExtract TVL1 optical flows in python (multi-process && multi-server)
PystepsPython framework for short-term ensemble prediction systems.
SpynetSpatial Pyramid Network for Optical Flow
FrvsrFrame-Recurrent Video Super-Resolution (official repository)
TfvosSemi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.
Flownet2 DockerDockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Video2tfrecordEasily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.
ArflowThe official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".
Netdef modelsRepository for different network models related to flow/disparity (ECCV 18)
VcnVolumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
Pwc Net pytorchpytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"
DdflowDDFlow: Learning Optical Flow with Unlabeled Data Distillation
Ficm🎮 [IJCAI'20][ICLR'19 Workshop] Flow-based Intrinsic Curiosity Module. Playing SuperMario with RL agent and FICM!
PytoflowThe py version of toflow → https://github.com/anchen1011/toflow
Dispnet Flownet DockerDockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Pwc NetPWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
EskfROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU
VoxelmorphUnsupervised Learning for Image Registration
PyoptflowOptical Flow estimation in pure Python
Adns3080Example code for the ADNS-3080 optical flow sensor
Flownet2FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
VppVideo++, a C++14 high performance video and image processing library.
PyflowFast, accurate and easy to run dense optical flow with python wrapper
LiteflownetLiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
TfoptflowOptical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)
Flownet2 TfFlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
CcCompetitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
SelflowSelFlow: Self-Supervised Learning of Optical Flow
ToflowTOFlow: Video Enhancement with Task-Oriented Flow
FastmotHigh-performance multiple object tracking based on YOLO, Deep SORT, and optical flow
Ransac Flow(ECCV 2020) RANSAC-Flow: generic two-stage image alignment
back2futureUnsupervised Learning of Multi-Frame Optical Flow with Occlusions
Real-Time-Abnormal-Events-Detection-and-Tracking-in-Surveillance-SystemThe main abnormal behaviors that this project can detect are: Violence, covering camera, Choking, lying down, Running, Motion in restricted areas. It provides much flexibility by allowing users to choose the abnormal behaviors they want to be detected and keeps track of every abnormal event to be reviewed. We used three methods to detect abnorma…
flownet2-ColabGoogle Colab notebook for running Nvidia flownet2-pytorch
pwcnetPWC-Network with TensorFlow
VoofVisual odometry using optical flow and neural networks
flow-io-opencvFork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].
SoftNet-SpotMEShallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos
EPPMCUDA implementation of the paper "Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow" in CVPR 2014.