75 Open source projects that are alternatives of or similar to pwcnet

Semi-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.

pytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"

OpenMMLab optical flow toolbox and benchmark

Extract TVL1 optical flows in python (multi-process && multi-server)

Unsupervised Learning for Image Registration

[ICCV 2021 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

ROS package for Correlation Flow (ICRA 2018)

The py version of toflow → https://github.com/anchen1011/toflow

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

ROS-based framework and RPi image to control PX4-powered drones 🍀

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Extract 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.

Spatial Pyramid Network for Optical Flow

Face Detection and tracking using CamShift, Kalman Filter, Optical Flow

Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)

Official repository of Learning Multi-Human Optical Flow (IJCV 2019)

Dense Matching Benchmark

Shallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos

DDFlow: Learning Optical Flow with Unlabeled Data Distillation

[MICCAI'18] Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

TensorFlow implementation for "Guided Optical Flow Learning"

Example code for the ADNS-3080 optical flow sensor

Python-based optical flow toolkit for existing popular dataset

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

Video++, a C++14 high performance video and image processing library.

Pure Pytorch implementation of Correlation Layer that commonly used in learning based optical flow estimator

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Vision-based Robot 3D Pose and Velocities Estimations

Python framework for short-term ensemble prediction systems.

Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding

Frame-Recurrent Video Super-Resolution (official repository)

A method about optimizing the facial landmark detection based on Kalman Filter, Optical Flow and Dlib

Collection of papers, datasets, code and other resources for object tracking and detection using deep learning

Caffe implementation for "Guided Optical Flow Learning"

Easily 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.

Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM.

Repository for different network models related to flow/disparity (ECCV 18)

Optical Flow Dataset and Benchmark for Visual Crowd Analysis

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

Visual odometry using optical flow and neural networks

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Image based obstacle avoidance using optical flow

🎮 [IJCAI'20][ICLR'19 Workshop] Flow-based Intrinsic Curiosity Module. Playing SuperMario with RL agent and FICM!

Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence, CVPR 2019

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

ROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU

CUDA implementation of the paper "Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow" in CVPR 2014.

Optical Flow estimation in pure Python

Depth and Flow for Visual Odometry

An implementation of several tracking algorithms based on Lucas Kanade algorithms

Attacking Optical Flow (ICCV 2019)

A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020

Multi-stream CNN architectures for action detection with actor-centric filtering

Fork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].

Compute dense optical flow using TV-L1 algorithm with NVIDIA GPU acceleration.

PyTrx 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.

[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency