Movement-induced Priors for Deep Stereo

10/18/2020
by   Yuxin Hou, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 3

page 5

page 7

04/12/2019

Multi-View Stereo by Temporal Nonparametric Fusion

We propose a novel idea for depth estimation from unstructured multi-vie...
10/11/2021

Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception

Stereo camera systems play an important role in robotics applications to...
11/01/2016

Stochastic Variational Deep Kernel Learning

Deep kernel learning combines the non-parametric flexibility of kernel m...
05/24/2019

Guided Stereo Matching

Stereo is a prominent technique to infer dense depth maps from images, a...
05/31/2019

DISCO: Depth Inference from Stereo using Context

Recent deep learning based approaches have outperformed classical stereo...
02/27/2012

Replica theory for learning curves for Gaussian processes on random graphs

Statistical physics approaches can be used to derive accurate prediction...
08/31/2018

A Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson's Disease

The assessment of Parkinson's disease (PD) poses a significant challenge...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.