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

From Computer Vision Freiburg:  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.

his video shows impressions from various parts of our dataset, as well as state-of-the-art realtime disparity estimation results produced by one of our new CNNs... (full paper)

 

 

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

The piCOBOT Electric vacuum generator

The piCOBOT Electric vacuum generator

Fully electric, slim design and absence of air-tubing and cabling. The new piCOBOT® Electric heads towards another success for Piab's piCOBOT® program. A secondary effect of these achievements is the absence of entangling air tubing and cabling. It simplifies the installation, and as the new piCOBOT® Electric only needs a single connection on the cobot arm, the clean set-up allows a completely unrestricted movement. The new piCOBOT® Electric package will contain plug & play software to fit UR e-series cobots, but many other useful adaptations will be introduced in the coming year