Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss

11/06/2020
by   Dongseok Shim, et al.
8

Estimating a depth map from a single RGB image has been investigated widely for localization, mapping, and 3-dimensional object detection. Recent studies on a single-view depth estimation are mostly based on deep Convolutional neural Networks (ConvNets) which require a large amount of training data paired with densely annotated labels. Depth annotation tasks are both expensive and inefficient, so it is inevitable to leverage RGB images which can be collected very easily to boost the performance of ConvNets without depth labels. However, most self-supervised learning algorithms are focused on capturing the semantic information of images to improve the performance in classification or object detection, not in depth estimation. In this paper, we show that existing self-supervised methods do not perform well on depth estimation and propose a gradient-based self-supervised learning algorithm with momentum contrastive loss to help ConvNets extract the geometric information with unlabeled images. As a result, the network can estimate the depth map accurately with a relatively small amount of annotated data. To show that our method is independent of the model structure, we evaluate our method with two different monocular depth estimation algorithms. Our method outperforms the previous state-of-the-art self-supervised learning algorithms and shows the efficiency of labeled data in triple compared to random initialization on the NYU Depth v2 dataset.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

research
07/28/2020

S^3Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data

Solving depth estimation with monocular cameras enables the possibility ...
research
08/27/2023

Calibrating Panoramic Depth Estimation for Practical Localization and Mapping

The absolute depth values of surrounding environments provide crucial cu...
research
04/13/2021

VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction

3D object detection and dense depth estimation are one of the most vital...
research
03/10/2021

Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss

Deep neural networks have been widely studied in autonomous driving appl...
research
12/19/2020

Self-supervised monocular depth estimation from oblique UAV videos

UAVs have become an essential photogrammetric measurement as they are af...
research
06/16/2020

Depth by Poking: Learning to Estimate Depth from Self-Supervised Grasping

Accurate depth estimation remains an open problem for robotic manipulati...
research
09/14/2020

Cascade Network for Self-Supervised Monocular Depth Estimation

It is a classical compute vision problem to obtain real scene depth maps...

Please sign up or login with your details

Forgot password? Click here to reset