A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

12/07/2015
by   Nikolaus Mayer, et al.
0

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

READ FULL TEXT

page 1

page 4

page 5

page 8

page 10

page 11

page 13

page 14

research
01/15/2018

Combining Stereo Disparity and Optical Flow for Basic Scene Flow

Scene flow is a description of real world motion in 3D that contains mor...
research
08/30/2018

Dense Scene Flow from Stereo Disparity and Optical Flow

Scene flow describes 3D motion in a 3D scene. It can either be modeled a...
research
07/19/2017

DenseNet for Dense Flow

Classical approaches for estimating optical flow have achieved rapid pro...
research
10/27/2019

SENSE: a Shared Encoder Network for Scene-flow Estimation

We introduce a compact network for holistic scene flow estimation, calle...
research
09/22/2021

A Novel Factor Graph-Based Optimization Technique for Stereo Correspondence Estimation

Dense disparities among multiple views is essential for estimating the 3...
research
07/03/2018

SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection

Detecting the occlusion from stereo images or video frames is important ...
research
01/19/2018

What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

The finding that very large networks can be trained efficiently and reli...

Please sign up or login with your details

Forgot password? Click here to reset