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

07/10/2020
by   Pierre Godet, et al.
0

We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results.

READ FULL TEXT

page 2

page 3

page 7

page 8

research
04/26/2023

SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation

Inaccurate optical flow estimates in and near occluded regions, and out-...
research
07/26/2019

Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM

Most of current Convolution Neural Network (CNN) based methods for optic...
research
12/01/2009

Mapping the spatiotemporal dynamics of calcium signaling in cellular neural networks using optical flow

An optical flow gradient algorithm was applied to spontaneously forming ...
research
02/25/2020

ScopeFlow: Dynamic Scene Scoping for Optical Flow

We propose to modify the common training protocols of optical flow, lead...
research
11/24/2022

Lightweight Event-based Optical Flow Estimation via Iterative Deblurring

Inspired by frame-based methods, state-of-the-art event-based optical fl...
research
11/09/2018

Learning Energy Based Inpainting for Optical Flow

Modern optical flow methods are often composed of a cascade of many inde...
research
04/10/2019

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

Deep learning approaches to optical flow estimation have seen rapid prog...

Please sign up or login with your details

Forgot password? Click here to reset