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.
Stars: ✭ 151 (+109.72%)
Pwc Net pytorchpytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"
Stars: ✭ 111 (+54.17%)
mmflowOpenMMLab optical flow toolbox and benchmark
Stars: ✭ 711 (+887.5%)
Py DenseflowExtract TVL1 optical flows in python (multi-process && multi-server)
Stars: ✭ 159 (+120.83%)
VoxelmorphUnsupervised Learning for Image Registration
Stars: ✭ 1,057 (+1368.06%)
flow1d[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation
Stars: ✭ 91 (+26.39%)
ArflowThe official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".
Stars: ✭ 134 (+86.11%)
correlation flowROS package for Correlation Flow (ICRA 2018)
Stars: ✭ 28 (-61.11%)
PytoflowThe py version of toflow → https://github.com/anchen1011/toflow
Stars: ✭ 83 (+15.28%)
UnflowUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
Stars: ✭ 239 (+231.94%)
CloverROS-based framework and RPi image to control PX4-powered drones 🍀
Stars: ✭ 177 (+145.83%)
Flownet2FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 938 (+1202.78%)
video featuresExtract video features from raw videos using multiple GPUs. We support RAFT and PWC flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, ResNet features.
Stars: ✭ 225 (+212.5%)
SpynetSpatial Pyramid Network for Optical Flow
Stars: ✭ 158 (+119.44%)
Flownet2 DockerDockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Stars: ✭ 137 (+90.28%)
humanflow2Official repository of Learning Multi-Human Optical Flow (IJCV 2019)
Stars: ✭ 37 (-48.61%)
SoftNet-SpotMEShallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos
Stars: ✭ 17 (-76.39%)
DdflowDDFlow: Learning Optical Flow with Unlabeled Data Distillation
Stars: ✭ 101 (+40.28%)
Pwc NetPWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
Stars: ✭ 1,142 (+1486.11%)
deepOFTensorFlow implementation for "Guided Optical Flow Learning"
Stars: ✭ 26 (-63.89%)
Adns3080Example code for the ADNS-3080 optical flow sensor
Stars: ✭ 36 (-50%)
OpticalflowtoolkitPython-based optical flow toolkit for existing popular dataset
Stars: ✭ 219 (+204.17%)
Opticalflow visualizationPython optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge
Stars: ✭ 183 (+154.17%)
VppVideo++, a C++14 high performance video and image processing library.
Stars: ✭ 655 (+809.72%)
CorrelationLayerPure Pytorch implementation of Correlation Layer that commonly used in learning based optical flow estimator
Stars: ✭ 22 (-69.44%)
Hidden Two StreamCaffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+148.61%)
PystepsPython framework for short-term ensemble prediction systems.
Stars: ✭ 159 (+120.83%)
EPCEvery Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
Stars: ✭ 27 (-62.5%)
FrvsrFrame-Recurrent Video Super-Resolution (official repository)
Stars: ✭ 157 (+118.06%)
GuidedNetCaffe implementation for "Guided Optical Flow Learning"
Stars: ✭ 28 (-61.11%)
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.
Stars: ✭ 137 (+90.28%)
PCLNetUnsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM.
Stars: ✭ 29 (-59.72%)
Netdef modelsRepository for different network models related to flow/disparity (ECCV 18)
Stars: ✭ 130 (+80.56%)
CrowdFlowOptical Flow Dataset and Benchmark for Visual Crowd Analysis
Stars: ✭ 87 (+20.83%)
VcnVolumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
Stars: ✭ 118 (+63.89%)
VoofVisual odometry using optical flow and neural networks
Stars: ✭ 59 (-18.06%)
Back2future.pytorchUnsupervised Learning of Multi-Frame Optical Flow with Occlusions
Stars: ✭ 104 (+44.44%)
Ficm🎮 [IJCAI'20][ICLR'19 Workshop] Flow-based Intrinsic Curiosity Module. Playing SuperMario with RL agent and FICM!
Stars: ✭ 92 (+27.78%)
BridgeDepthFlowBridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence, CVPR 2019
Stars: ✭ 114 (+58.33%)
Dispnet Flownet DockerDockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Stars: ✭ 78 (+8.33%)
Maskflownet[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
Stars: ✭ 242 (+236.11%)
EskfROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU
Stars: ✭ 63 (-12.5%)
EPPMCUDA implementation of the paper "Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow" in CVPR 2014.
Stars: ✭ 34 (-52.78%)
PyoptflowOptical Flow estimation in pure Python
Stars: ✭ 49 (-31.94%)
Df VoDepth and Flow for Visual Odometry
Stars: ✭ 233 (+223.61%)
flowattackAttacking Optical Flow (ICCV 2019)
Stars: ✭ 58 (-19.44%)
Liteflownet2A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (+170.83%)
deep-action-detectionMulti-stream CNN architectures for action detection with actor-centric filtering
Stars: ✭ 24 (-66.67%)
flow-io-opencvFork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].
Stars: ✭ 20 (-72.22%)
Optical-Flow-GPU-DockerCompute dense optical flow using TV-L1 algorithm with NVIDIA GPU acceleration.
Stars: ✭ 48 (-33.33%)
PyTrxPyTrx is a Python object-oriented programme created for the purpose of calculating real-world measurements from oblique images and time-lapse image series. Its primary purpose is to obtain velocities, surface areas, and distances from oblique, optical imagery of glacial environments.
Stars: ✭ 31 (-56.94%)
Df Net[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
Stars: ✭ 190 (+163.89%)