DeMoN: Depth and Motion Network for Learning Monocular Stereo

12/07/2016
by   Benjamin Ummenhofer, et al.
0

In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple stacked encoder-decoder networks, the core part being an iterative network that is able to improve its own predictions. The network estimates not only depth and motion, but additionally surface normals, optical flow between the images and confidence of the matching. A crucial component of the approach is a training loss based on spatial relative differences. Compared to traditional two-frame structure from motion methods, results are more accurate and more robust. In contrast to the popular depth-from-single-image networks, DeMoN learns the concept of matching and, thus, better generalizes to structures not seen during training.

READ FULL TEXT

page 7

page 8

page 13

page 15

page 16

page 17

page 18

page 21

research
12/11/2018

DeepV2D: Video to Depth with Differentiable Structure from Motion

We propose DeepV2D, an end-to-end differentiable deep learning architect...
research
09/12/2019

Flow-Motion and Depth Network for Monocular Stereo and Beyond

We propose a learning-based method that solves monocular stereo and can ...
research
06/27/2018

Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

Learning to estimate 3D geometry in a single image by watching unlabeled...
research
09/12/2018

End-to-end depth from motion with stabilized monocular videos

We propose a depth map inference system from monocular videos based on a...
research
07/15/2022

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

In this paper we propose USegScene, a framework for semantically guided ...
research
05/24/2018

LF-Net: Learning Local Features from Images

We present a novel deep architecture and a training strategy to learn a ...
research
12/21/2020

Monocular Depth Parameterizing Networks

Monocular depth estimation is a highly challenging problem that is often...

Please sign up or login with your details

Forgot password? Click here to reset