RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning

TL;DR

This paper introduces RealRep, a novel framework for converting SDR to HDR by disentangling luminance and chrominance, improving robustness and generalization across diverse SDR content.

Contribution

The paper proposes a generalized SDR-to-HDR conversion method using attribute-disentangled representations and a degradation-aware mapping network, advancing beyond fixed tone mapping techniques.

Findings

RealRep outperforms existing methods in generalization and perceptual quality.

The attribute-disentangled approach effectively captures content variations across SDR styles.

The DDACMNet framework enables adaptive, degradation-conditioned HDR mapping.

Abstract

High-Dynamic-Range Wide-Color-Gamut (HDR-WCG) technology is becoming increasingly widespread, driving a growing need for converting Standard Dynamic Range (SDR) content to HDR. Existing methods primarily rely on fixed tone mapping operators, which struggle to handle the diverse appearances and degradations commonly present in real-world SDR content. To address this limitation, we propose a generalized SDR-to-HDR framework that enhances robustness by learning attribute-disentangled representations. Central to our approach is Realistic Attribute-Disentangled Representation Learning (RealRep), which explicitly disentangles luminance and chrominance components to capture intrinsic content variations across different SDR distributions. Furthermore, we design a Luma-/Chroma-aware negative exemplar generation strategy that constructs degradation-sensitive contrastive pairs, effectively modeling tone discrepancies across SDR styles. Building on these attribute-level priors, we introduce the Degradation-Domain Aware Controlled Mapping Network (DDACMNet), a lightweight, two-stage framework that performs adaptive hierarchical mapping guided by a control-aware normalization mechanism. DDACMNet dynamically modulates the mapping process via degradation-conditioned features, enabling robust adaptation across diverse degradation domains. Extensive experiments demonstrate that RealRep consistently outperforms state-of-the-art methods in both generalization and perceptually faithful HDR color gamut reconstruction.