optical-flow

CoTracker is a model for tracking any point (pixel) on a video.

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

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

Unsupervised Learning for Image Registration

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

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

OpenMMLab optical flow toolbox and benchmark

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

[CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching

Fast, accurate and easy to run dense optical flow with python wrapper

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

Depth and Flow for Visual Odometry

This is a list of awesome paper about optical flow and related work.

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

A project that uses optical flow and machine learning to detect aimhacking in video clips.

Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)

Python framework for short-term ensemble prediction systems.