An efficient encoder–decoder model for portrait depth estimation from single images trained on pixel-accurate synthetic data

Depth estimation from a single image frame is a fundamental challenge in computer vision, with many applications such as augmented reality, action recognition, image understanding, and autonomous driving. Large and diverse training sets are required for accurate depth estimation from a single image...

Full description

Saved in:
Bibliographic Details
Published in:Neural networks Vol. 142; pp. 479 - 491
Main Authors: Khan, Faisal, Hussain, Shahid, Basak, Shubhajit, Lemley, Joseph, Corcoran, Peter
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.10.2021
Subjects:
2.5D dataset
Convolution neural network
Depth estimation
Encoder–decoder architecture
Facial depth
Hybrid loss function
Hybrid loss function
Encoder–decoder architecture
2.5D dataset
Depth estimation
Convolution neural network
Facial depth
ISSN:0893-6080, 1879-2782, 1879-2782
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Depth estimation from a single image frame is a fundamental challenge in computer vision, with many applications such as augmented reality, action recognition, image understanding, and autonomous driving. Large and diverse training sets are required for accurate depth estimation from a single image frame. Due to challenges in obtaining dense ground-truth depth, a new 3D pipeline of 100 synthetic virtual human models is presented to generate multiple 2D facial images and corresponding ground truth depth data, allowing complete control over image variations. To validate the synthetic facial depth data, we propose an evaluation of state-of-the-art depth estimation algorithms based on single image frames on the generated synthetic dataset. Furthermore, an improved encoder–decoder based neural network is presented. This network is computationally efficient and shows better performance than current state-of-the-art when tested and evaluated across 4 public datasets. Our training methodology relies on the use of synthetic data samples which provides a more reliable ground truth for depth estimation. Additionally, using a combination of appropriate loss functions leads to improved performance than the current state-of-the-art network performances. Our approach clearly outperforms competing methods across different test datasets, setting a new state-of-the-art for facial depth estimation from synthetic data.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2021.07.007