# Optical Flow Estimation

444 papers with code • 9 benchmarks • 29 datasets

**Optical Flow Estimation** is the problem of finding pixel-wise motions between consecutive images.

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

## Libraries

Use these libraries to find Optical Flow Estimation models and implementations## Datasets

## Most implemented papers

# FlowNet: Learning Optical Flow with Convolutional Networks

Optical flow estimation has not been among the tasks where CNNs were successful.

# PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow.

# RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

We propose RIFE, a Real-time Intermediate Flow Estimation algorithm for Video Frame Interpolation (VFI).

# Optical Flow Estimation using a Spatial Pyramid Network

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning.

# FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.

# Semantic Flow for Fast and Accurate Scene Parsing

A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.

# RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes.

# Perceiver IO: A General Architecture for Structured Inputs & Outputs

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.

# Two-Stream Convolutional Networks for Action Recognition in Videos

Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.

# Video Frame Interpolation via Adaptive Separable Convolution

Our method develops a deep fully convolutional neural network that takes two input frames and estimates pairs of 1D kernels for all pixels simultaneously.