Dual Inverse Degradation Network for Real-World SDRTV-to-HDRTV Conversion

TL;DR

This study proposes Dual Inversion Downgraded SDRTV to HDRTV Network (DIDNet), which can accurately perform inverse tone mapping while preventing encoding artifacts from being amplified, thereby significantly improving visual quality.

Abstract

In this study, we address the emerging necessity of converting Standard Dynamic Range Television (SDRTV) content into High Dynamic Range Television (HDRTV) in light of the limited number of native HDRTV content. A principal technical challenge in this conversion is the exacerbation of coding artifacts inherent in SDRTV, which detrimentally impacts the quality of the resulting HDRTV. To address this issue, our method introduces a novel approach that conceptualizes the SDRTV-to-HDRTV conversion as a composite task involving dual degradation restoration. This encompasses inverse tone mapping in conjunction with video restoration. We propose Dual Inversion Downgraded SDRTV to HDRTV Network (DIDNet), which can accurately perform inverse tone mapping while preventing encoding artifacts from being amplified, thereby significantly improving visual quality. DIDNet integrates an intermediate auxiliary loss function to effectively separate the dual degradation restoration tasks and efficient learning of both artifact reduction and inverse tone mapping during end-to-end training. Additionally, DIDNet introduces a spatio-temporal feature alignment module for video frame fusion, which augments texture quality and reduces artifacts. The architecture further includes a dual-modulation convolution mechanism for optimized inverse tone mapping. Recognizing the richer texture and high-frequency information in HDRTV compared to SDRTV, we further introduce a wavelet attention module to enhance frequency features. Our approach demonstrates marked superiority over existing state-of-the-art techniques in terms of quantitative performance and visual quality.

Figures (8)

• Figure 1: (a) Real-world SDRTV-to-HDRTV application scenario. Due to distribution copyright and historical technical limitations, media distribution companies hardly obtain high-quality (HQ) SDRTV (nearly lossless) and only possess relatively low-quality (LQ) versions. (b) Workflow of previous HQ SDRTV to HQ HDRTV methods. When using these methods with LQ SDRTV in the real world, encoding artifacts are amplified, leading to degraded performance. (c) Workflow of our proposed real-world SDRTV-to-HDRTV method. We propose a dual inverse degradation restoration network to remove encoding artifacts and generate high-fidelity HDRTV results simultaneously.
• Figure 2: Banding produced by different methods. Previous methods amplify coding artifacts, which can result in subjective quality degradation of the resulting HDRTV.
• Figure 3: Frequency information comparison. HDRTV has more information in the high frequency area than SDRTV. SDRTV-HH and HDRTV-HH represent the high-frequency subbands obtained by SDRTV and HDRTV through wavelet transform respectively.
• Figure 4: (a) Framework summary. Our framework consists of four parts. (b) Multi-frame alignment artifact repair: Temporal-Spatial Alignment Fusion module TSAF. (c) High-frequency information enhancement: Feature Frequency Enhancement module FFE. (d) Multi-frame color prior extraction: 3D ConditionNet 3DCN. (e) Fast color tone mapping: Dual Modulation Inverse Tone Mapping module DMITM.
• Figure 5: The structure of the Wavelet Attention (WA) module.