PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction

2025-09-20

AI Summary

Existing LDR-to-HDR conversion methods lack joint modeling of illumination, material properties, and scene geometry, limiting physical plausibility and detail fidelity in HDR reconstruction. This paper proposes the first generative HDR reconstruction framework that explicitly integrates illumination, material (specular/diffuse) components, and geometry (depth). Built upon a latent diffusion model, our approach conditions the denoising process on illumination and depth maps, while introducing a material-aware physical loss function to enforce physically consistent interactions between reflectance properties and lighting. To our knowledge, this is the first method enabling joint, physics-based modeling of material and illumination in HDR reconstruction. It significantly improves visual realism, preserves fine-grained highlight/shadow details, and ensures cross-material consistency. Extensive evaluations on multiple benchmarks demonstrate state-of-the-art performance, with superior quantitative metrics and compelling subjective quality validated through human assessment.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Low Dynamic Range (LDR) to High Dynamic Range (HDR) image translation is a fundamental task in many computational vision problems. Numerous data-driven methods have been proposed to address this problem; however, they lack explicit modeling of illumination, lighting, and scene geometry in images. This limits the quality of the reconstructed HDR images. Since lighting and shadows interact differently with different materials, (e.g., specular surfaces such as glass and metal, and lambertian or diffuse surfaces such as wood and stone), modeling material-specific properties (e.g., specular and diffuse reflectance) has the potential to improve the quality of HDR image reconstruction. This paper presents PhysHDR, a simple yet powerful latent diffusion-based generative model for HDR image reconstruction. The denoising process is conditioned on lighting and depth information and guided by a novel loss to incorporate material properties of surfaces in the scene. The experimental results establish the efficacy of PhysHDR in comparison to a number of recent state-of-the-art methods.

Problem

• Reconstructing HDR images from LDR inputs lacks explicit lighting modeling
• Existing methods ignore material-specific properties like specular reflectance
• Current approaches fail to incorporate scene geometry in HDR reconstruction

Innovation

• Latent diffusion model conditioned on lighting and depth
• Novel loss function incorporating material reflectance properties
• Explicit modeling of specular and diffuse surface interactions