Pwc NetPWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
Stars: ✭ 1,142 (+1868.97%)
OpticalflowtoolkitPython-based optical flow toolkit for existing popular dataset
Stars: ✭ 219 (+277.59%)
Flownet2 DockerDockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Stars: ✭ 137 (+136.21%)
PyflowFast, accurate and easy to run dense optical flow with python wrapper
Stars: ✭ 564 (+872.41%)
DdflowDDFlow: Learning Optical Flow with Unlabeled Data Distillation
Stars: ✭ 101 (+74.14%)
SimP-GCNImplementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Stars: ✭ 43 (-25.86%)
Adns3080Example code for the ADNS-3080 optical flow sensor
Stars: ✭ 36 (-37.93%)
CloverROS-based framework and RPi image to control PX4-powered drones 🍀
Stars: ✭ 177 (+205.17%)
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 (+160.34%)
CcCompetitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
Stars: ✭ 348 (+500%)
mmflowOpenMMLab optical flow toolbox and benchmark
Stars: ✭ 711 (+1125.86%)
ArflowThe official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".
Stars: ✭ 134 (+131.03%)
geometric advGeometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)
Stars: ✭ 20 (-65.52%)
Pwc Net pytorchpytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"
Stars: ✭ 111 (+91.38%)
UnflowUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
Stars: ✭ 239 (+312.07%)
PytoflowThe py version of toflow → https://github.com/anchen1011/toflow
Stars: ✭ 83 (+43.1%)
EPCEvery Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
Stars: ✭ 27 (-53.45%)
VoxelmorphUnsupervised Learning for Image Registration
Stars: ✭ 1,057 (+1722.41%)
Df Net[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
Stars: ✭ 190 (+227.59%)
Flownet2FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 938 (+1517.24%)
Pro-GNNImplementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Stars: ✭ 202 (+248.28%)
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)
Stars: ✭ 415 (+615.52%)
Py DenseflowExtract TVL1 optical flows in python (multi-process && multi-server)
Stars: ✭ 159 (+174.14%)
FrvsrFrame-Recurrent Video Super-Resolution (official repository)
Stars: ✭ 157 (+170.69%)
SelflowSelFlow: Self-Supervised Learning of Optical Flow
Stars: ✭ 319 (+450%)
grbGraph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.
Stars: ✭ 70 (+20.69%)
POPQORNAn Algorithm to Quantify Robustness of Recurrent Neural Networks
Stars: ✭ 44 (-24.14%)
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 (+136.21%)
Netdef modelsRepository for different network models related to flow/disparity (ECCV 18)
Stars: ✭ 130 (+124.14%)
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 (+287.93%)
VcnVolumetric Correspondence Networks for Optical Flow, NeurIPS 2019.
Stars: ✭ 118 (+103.45%)
Maskflownet[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
Stars: ✭ 242 (+317.24%)
Back2future.pytorchUnsupervised Learning of Multi-Frame Optical Flow with Occlusions
Stars: ✭ 104 (+79.31%)
generative adversaryCode for the unrestricted adversarial examples paper (NeurIPS 2018)
Stars: ✭ 58 (+0%)
Ficm🎮 [IJCAI'20][ICLR'19 Workshop] Flow-based Intrinsic Curiosity Module. Playing SuperMario with RL agent and FICM!
Stars: ✭ 92 (+58.62%)
Df VoDepth and Flow for Visual Odometry
Stars: ✭ 233 (+301.72%)
Dispnet Flownet DockerDockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Stars: ✭ 78 (+34.48%)
CorrelationLayerPure Pytorch implementation of Correlation Layer that commonly used in learning based optical flow estimator
Stars: ✭ 22 (-62.07%)
EskfROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU
Stars: ✭ 63 (+8.62%)
Liteflownet2A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (+236.21%)
PyoptflowOptical Flow estimation in pure Python
Stars: ✭ 49 (-15.52%)
humanflow2Official repository of Learning Multi-Human Optical Flow (IJCV 2019)
Stars: ✭ 37 (-36.21%)
Opticalflow visualizationPython optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge
Stars: ✭ 183 (+215.52%)
VppVideo++, a C++14 high performance video and image processing library.
Stars: ✭ 655 (+1029.31%)
flow1d[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation
Stars: ✭ 91 (+56.9%)
LiteflownetLiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Stars: ✭ 474 (+717.24%)
Hidden Two StreamCaffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+208.62%)
Flownet2 TfFlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 378 (+551.72%)
CrowdFlowOptical Flow Dataset and Benchmark for Visual Crowd Analysis
Stars: ✭ 87 (+50%)
PystepsPython framework for short-term ensemble prediction systems.
Stars: ✭ 159 (+174.14%)
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 (-46.55%)
AdvPCAdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)
Stars: ✭ 35 (-39.66%)
GuidedNetCaffe implementation for "Guided Optical Flow Learning"
Stars: ✭ 28 (-51.72%)
SpynetSpatial Pyramid Network for Optical Flow
Stars: ✭ 158 (+172.41%)