ePBR: Extended PBR Materials in Image Synthesis

2025-04-23

AI Summary

Existing PBR methods struggle to model highly specular and transparent materials (e.g., glass, windows) with physical consistency, leading to reflection-transmission coupling artifacts in photorealistic indoor/outdoor image synthesis. This paper introduces the first physics-driven framework that explicitly incorporates transmission properties into intrinsic image representation—extending the PBR material model and enabling joint reflection-transmission decomposition. The result is an interpretable, deterministic, and explicit synthesis paradigm. Our method supports physically grounded, pixel-level material parameter editing while strictly preserving energy conservation and reciprocity, thereby significantly improving synthesis fidelity and rendering efficiency for transparent materials. Key contributions include: (1) the first transmission-aware intrinsic image representation; (2) an explicit reflection-transmission decoupling mechanism grounded in physical optics; and (3) high-fidelity, editable, and computationally efficient photorealistic synthesis of transparent materials.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Realistic indoor or outdoor image synthesis is a core challenge in computer vision and graphics. The learning-based approach is easy to use but lacks physical consistency, while traditional Physically Based Rendering (PBR) offers high realism but is computationally expensive. Intrinsic image representation offers a well-balanced trade-off, decomposing images into fundamental components (intrinsic channels) such as geometry, materials, and illumination for controllable synthesis. However, existing PBR materials struggle with complex surface models, particularly high-specular and transparent surfaces. In this work, we extend intrinsic image representations to incorporate both reflection and transmission properties, enabling the synthesis of transparent materials such as glass and windows. We propose an explicit intrinsic compositing framework that provides deterministic, interpretable image synthesis. With the Extended PBR (ePBR) Materials, we can effectively edit the materials with precise controls.

Problem

• Extend intrinsic image representations for reflection and transmission properties
• Improve synthesis of transparent materials like glass and windows
• Provide deterministic, interpretable image synthesis with ePBR materials

Innovation

• Extends intrinsic image representations for reflection and transmission
• Proposes explicit intrinsic compositing framework for interpretable synthesis
• Enables precise material editing with Extended PBR (ePBR) Materials