Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction

03/18/2019
by   Alex Wong, et al.
12

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene structure without direct supervision. Although we train a network with stereo pairs, we only require a single image at test time to hypothesize disparity or depth. We propose a novel objective function that exploits the bilateral cyclic relationship between the left and right disparities and we introduce an adaptive regularization scheme that allows the network to handle both the co-visible and occluded regions in a stereo pair. This process ultimately produces a model to generate hypotheses for the 3-dimensional structure of the scene as viewed in a single image. When used to generate a single (most probable) estimate of depth, our method outperforms state-of-the-art unsupervised monocular depth prediction methods on the KITTI benchmarks. We show that our method generalizes well by applying our models trained on KITTI to the Make3d dataset.

READ FULL TEXT

page 6

page 7

page 8

research
07/24/2020

A Lightweight Neural Network for Monocular View Generation with Occlusion Handling

In this article, we present a very lightweight neural network architectu...
research
05/06/2019

PackNet-SfM: 3D Packing for Self-Supervised Monocular Depth Estimation

Densely estimating the depth of a scene from a single image is an ill-po...
research
02/13/2023

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

We introduce VA-DepthNet, a simple, effective, and accurate deep neural ...
research
03/31/2023

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Neural-network-based single image depth prediction (SIDP) is a challengi...
research
08/20/2018

Learning Monocular Depth by Distilling Cross-domain Stereo Networks

Monocular depth estimation aims at estimating a pixelwise depth map for ...
research
09/30/2019

Depth Estimation in Nighttime using Stereo-Consistent Cyclic Translations

Most existing methods of depth from stereo are designed for daytime scen...
research
07/30/2018

Geo-Supervised Visual Depth Prediction

We propose using global orientation from inertial measurements, and the ...

Please sign up or login with your details

Forgot password? Click here to reset