RealRep: Generalized SDR-to-HDR Conversion with Style Disentangled Representation Learning

2025-05-12

AI Summary

Existing SDR-to-HDR methods rely on fixed tone mapping operators, limiting generalization across diverse real-world SDR content styles. To address this, we propose DDACMNet, a style-adaptive inverse tone mapping framework. Our method introduces the first style-decoupled multi-view representation learning scheme and constructs a degradation-aware, two-stage controllable mapping architecture, integrating control-aware normalization with hierarchical feature dynamic modulation. Critically, DDACMNet achieves robust HDR/WCG reconstruction across heterogeneous styles without requiring explicit style labels. Extensive experiments demonstrate significant improvements over state-of-the-art methods on multiple benchmarks, notably enhancing both generalizability and perceptual fidelity. To our knowledge, this is the first approach enabling high-fidelity, style-adaptive, and universally applicable SDR-to-HDR conversion.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

High-Dynamic-Range Wide-Color-Gamut (HDR-WCG) technology is becoming increasingly prevalent, intensifying the demand for converting Standard Dynamic Range (SDR) content to HDR. Existing methods primarily rely on fixed tone mapping operators, which are inadequate for handling SDR inputs with diverse styles commonly found in real-world scenarios. To address this challenge, we propose a generalized SDR-to-HDR method that handles diverse styles in real-world SDR content, termed Realistic Style Disentangled Representation Learning (RealRep). By disentangling luminance and chrominance, we analyze the intrinsic differences between contents with varying styles and propose a disentangled multi-view style representation learning method. This approach captures the guidance prior of true luminance and chrominance distributions across different styles, even when the SDR style distributions exhibit significant variations, thereby establishing a robust embedding space for inverse tone mapping. Motivated by the difficulty of directly utilizing degradation representation priors, we further introduce the Degradation-Domain Aware Controlled Mapping Network (DDACMNet), a two-stage framework that performs adaptive hierarchical mapping guided by a control-aware normalization mechanism. DDACMNet dynamically modulates the mapping process via degradation-conditioned hierarchical features, enabling robust adaptation across diverse degradation domains. Extensive experiments show that RealRep consistently outperforms state-of-the-art methods with superior generalization and perceptually faithful HDR color gamut reconstruction.

Problem

• Convert diverse SDR content to HDR effectively
• Handle varying SDR styles with disentangled representation learning
• Achieve robust inverse tone mapping across degradation domains

Innovation

• Style Disentangled Representation Learning for SDR-to-HDR
• Degradation-Domain Aware Controlled Mapping Network
• Adaptive hierarchical mapping with control-aware normalization