Abstract

Co-authors: Patrick Knöbelreiter (Graz University of Technology), Alexander Shekhovtsov (Technical University of Prague), Gottfried Munda (Graz University of Technology), Christian Reinbacher (Amazon)

For many years, discrete optimization models such as conditional random fields (CRFs) have defined the state-of-the-art for classical correspondence problems such as motion and stereo. One of the most important ingredients in those models is the choice of the feature transform that is used to compute the similarity between images patches. For a long time, hand crafted features such as the celebrated scale invariant feature transform (SIFT) defined the state-of-the-art. Triggered by the recent success of convolutional neural networks (CNNs), it is quite natural to learn such a feature transform from data. In this talk, I will show how to efficiently learn such CNN features from data using an end-to-end learning approach. It turns out that our learned models yields state-of-the-art results on a number of established benchmark databases.

Related Links

• https://arxiv.org/pdf/1707.06427 – Scalable Full Flow with Learned Binary Descriptors
• https://arxiv.org/pdf/1611.10229 – End-to-End Training of Hybrid CNN -CRF Models for Stereo