Official implementation of ICCV2023 VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation

This repository is the official implementation of "SKFlow: Learning Optical Flow with Super Kernels" .

Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation

[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

[IJCV 2023 / ECCV RVC 2022 Winner] Inference code for "MS-RAFT+: High Resolution Multi-Scale RAFT", the 2022 Robust Vision Challenge winner in the category "Optical Flow"

[CVPR 2023] Rethinking Optical Flow from Geometric Matching Consistent Perspective

LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation

Code for Hierarchical Discrete Distribution Decomposition for Match Density Estimation (CVPR 2019)

Global Matching with Overlapping Attention for Optical Flow Estimation, CVPR 2022

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

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

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

[ICCV'21 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

DIP:Deep Inverse Patchmatch for High-Resolution Optical Flow(CVPR2022)

[IV2022] pytorch implementation for 'CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving'

CRAFT: Cross-Attentional Flow Transformers for Optical Flow Estimation

[WACV 2024] Code for "CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning"

Source code for CVPR 2024 paper UnSAMFlow Unsupervised Optical Flow Guided by Segment Anything Model.

A repository of AAAI 2024 paper 'SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model'

[IJCV 2024] SplatFlow: Learning Multi-frame Optical Flow via Splatting

[CVPR 2024] MemFlow: Optical Flow Estimation and Prediction with Memory

Taming Transformers for High-Resolution Image Synthesis

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation (ICRA 2021)

Four landmark detection algorithms, implemented in PyTorch.

Learning to Estimate Hidden Motions with Global Motion Aggregation (ICCV 2021)