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

SCHUNK's New Safety Gripping System EGN

SCHUNK's New Safety Gripping System EGN

With the SLS, SOS, and STO functionalities, the SCHUNK EGN gripping system certified in accordance with DIN EN ISO 13849 enables safe human/machine collaboration. If the production process is interrupted by an emergency shut-off, the SCHUNK EGN goes into either a safely limited speed mode or a safe stop mode depending on the activated protection zone. In contrast to other solutions available on the market, the SCHUNK safety gripping system is continuously powered even in the safe operating stop so that the gripped parts are reliably held even without mechanical maintenance of gripping force. As soon as the protection zone is released, the gripper immediately switches back to the regular operating mode without the system having to be restarted.