Optical Flow Estimation
652 papers with code • 10 benchmarks • 34 datasets
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
Benchmarks
These leaderboards are used to track progress in Optical Flow Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Optical Flow Estimation models and implementationsDatasets
KITTI
FlyingThings3D
Vimeo90K
MPI Sintel
Virtual KITTI
MegaDepth
VisDrone
Event-Camera Dataset
N-CARS
MVSEC
Most implemented papers
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
twhui/LiteFlowNet
•
•
CVPR 2018
FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation.
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
BehradToghi/ECCV_Youtube_VOS
•
•
ECCV 2018
End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
DGC-Net: Dense Geometric Correspondence Network
This paper addresses the challenge of dense pixel correspondence estimation between two images.
DVC: An End-to-end Deep Video Compression Framework
Conventional video compression approaches use the predictive coding architecture and encode the corresponding motion information and residual information.
Temporal Interlacing Network
deepcs233/TIN
•
•
In this way, a heavy temporal model is replaced by a simple interlacing operator.
Towards Better Generalization: Joint Depth-Pose Learning without PoseNet
B1ueber2y/TrianFlow
•
•
CVPR 2020
In this work, we tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning.
Learning Accurate Dense Correspondences and When to Trust Them
PruneTruong/PDCNet
•
•
CVPR 2021
Establishing dense correspondences between a pair of images is an important and general problem.
Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
The code and protocols for our benchmark and algorithm are available at https://github. com/TuSimple/LiDAR_SOT/.
GMFlow: Learning Optical Flow via Global Matching
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements.
BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
In the field of phase change phenomena, the lack of accessible and diverse datasets suitable for machine learning (ML) training poses a significant challenge.
