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

TL;DR

This paper presents DIDNet, a novel neural network that effectively converts SDRTV to HDRTV by addressing artifacts and enhancing quality through dual degradation restoration, inverse tone mapping, and advanced feature alignment.

Contribution

The paper introduces DIDNet, a comprehensive model that combines inverse tone mapping, artifact reduction, and spatio-temporal feature alignment for improved SDRTV to HDRTV conversion.

Findings

DIDNet outperforms existing methods in quantitative metrics.

Significant improvement in visual quality and artifact suppression.

Effective separation of dual degradation tasks during training.

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.