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

Destaco Automatic Tool Changers

Destaco Automatic Tool Changers

Automatically change end effector tooling quickly and easily with Destaco's Automatic Tool Changers. Designed with exceptional repeatability, high rigidity and load capacity, they are perfect for multiple tooling applications utilizing one robot. We offer different models and sizes to handle light-duty to heavy-duty applications. Our RQC/RTP Series provides a high level of flexibility with a configurable, modular design that accommodates up to four optional modular interfaces.