Citation: Park, J.; Song, B.C. Cyclic
Learning-Based Lightweight
Network for Inverse Tone Mapping.
Electronics 2022, 11, 2436. https://
doi.org/10.3390/electronics11152436
Academic Editor: Savvas A.
Chatzichristofis
Received: 28 June 2022
Accepted: 1 August 2022
Published: 4 August 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Cyclic Learning-Based Lightweight Network for Inverse
Tone Mapping
Jiyun Park
1,2
and Byung Cheol Song
2,
*
1
LX Semicon, Seoul 06763, Korea
2
Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Korea
* Correspondence: bcsong@inha.ac.kr; Tel.: +82-32-860-7413
Abstract:
Recent studies on inverse tone mapping (iTM) have moved toward indirect mapping,
which generates a stack of low dynamic range (LDR) images with multiple exposure values (multi-EV
stack) and then merges them. In order to generate multi-EV stack(s), several large-scale networks with
more than 20 M parameters have been proposed, but their high dynamic range (HDR) reconstruction
and multi-EV stack generation performance were not acceptable. Also, some previous methods
using cycle consistency should even have trained additional networks that are not used for multi-
EV stack generation, which results in large memory for training. Thus, this paper proposes novel
cyclic learning based on cycle consistency to reduce the memory burden in training. In detail, we
eliminated networks used only for training, so the proposed method enables efficient learning in
terms of training-purpose memory. In addition, this paper presents a lightweight iTM network that
dramatically reduces the network sizes of the existing networks. Actually, the proposed lightweight
network requires only a small parameter size of 1/100 compared to the state-of-the-art (SOTA)
method. The lightweight network contributes to the practical use of iTM. Therefore, the proposed
method based on a lightweight network reliably generates a multi-EV stack. Experimental results
show that the proposed method achieves quantitatively SOTA performance and is qualitatively
comparable to conventional indirect iTM methods.
Keywords: cyclic learning; inverse tone mapping; lightweight network
1. Introduction
With the rapid development of deep learning, a lot of methods for reconstructing a
high dynamic range (HDR) image from low dynamic range (LDR) image(s) have been
proposed [
1
–
4
]. They can be largely divided into two categories. The first one is the
multiexposure fusion (MEF) approach [
5
–
7
] in which LDR images of different exposure
values (EVs) are acquired and merged to generate a single HDR image. Conventional MEF
methods often suffer from ghost artifacts due to moving object(s) while acquiring multiple
LDR images with parallax. The second one is so-called inverse tone mapping (iTM) [
8
–
14
],
which reconstructs an HDR image using only a single LDR image.
Meanwhile, the iTM approach is again classified into direct iTM and indirect iTM.
Direct iTM is literally a one-to-one tone mapping between LDR and HDR [
8
,
10
,
14
]. Whereas
direct iTM uses only one LDR, indirect iTM synthesizes LDRs of multiple EVs (multi-EV
stack) from a single LDR and merges them to generate an HDR [
9
,
11
–
13
]. For example,
deep chain HDRI [
12
] employs a strategy to allocate a subnetwork for each target EV.
As such, the subnetworks tend to increase as much as the number of target EVs, which
can be computationally burdensome. On the other hand, DrTMO [
9
], deep recursive
HDRI [
11
], and deep cycle HDRI [
13
] generate a multi-EV stack by using EV up/down
networks in consideration of the increasing/decreasing direction toward a target EV. In
addition, [
15
] proposed generating HDR images using LDR video sequence information.
As iTM methods develop, the network parameter size has also increased. Unfortunately,
Electronics 2022, 11, 2436. https://doi.org/10.3390/electronics11152436 https://www.mdpi.com/journal/electronics
