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

Bota Systems - The SensONE 6-axis force torque sensor for robots

Bota Systems - The SensONE 6-axis force torque sensor for robots

Our Bota Systems force torque sensors, like the SensONE, are designed for collaborative and industrial robots. It enables human machine interaction, provides force, vision and inertia data and offers "plug and work" foll all platforms. The compact design is dustproof and water-resistant. The ISO 9409-1-50-4-M6 mounting flange makes integrating the SensONE sensor with robots extremely easy. No adapter is needed, only fasteners! The SensONE sensor is a one of its kind product and the best solution for force feedback applications and collaborative robots at its price. The SensONE is available in two communication options and includes software integration with TwinCAT, ROS, LabVIEW and MATLAB®.