Movement-induced priors for deep stereo

Yuxin Hou, Muhammad Kamran Janjua, Juho Kannala, Arno Solin

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review


We propose a method for fusing stereo disparity estimation with movement-induced prior information. Instead of independent inference frame-by-frame, we formulate the problem as a non-parametric learning task in terms of a temporal Gaussian process prior with a movement-driven kernel for inter-frame reasoning. We present a hierarchy of three Gaussian process kernels depending on the availability of motion information, where our main focus is on a new gyroscope-driven kernel for handheld devices with low-quality MEMS sensors, thus also relaxing the requirement of having full 6D camera poses available. We show how our method can be combined with two state-of-the-art deep stereo methods. The method either work in a plug-and-play fashion with pre-trained deep stereo networks, or further improved by jointly training the kernels together with encoder-decoder architectures, leading to consistent improvement.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
Number of pages8
ISBN (Electronic)9781728188089
Publication statusPublished - 2020
MoE publication typeA4 Conference publication
EventInternational Conference on Pattern Recognition - Virtual, Online, Milan, Italy
Duration: 10 Jan 202115 Jan 2021
Conference number: 25

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


ConferenceInternational Conference on Pattern Recognition
Abbreviated titleICPR


Dive into the research topics of 'Movement-induced priors for deep stereo'. Together they form a unique fingerprint.

Cite this