Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects

2025-10-02

AI Summary

Accurately reconstructing and relighting glossy objects is challenging due to strong coupling among geometry, material, and illumination. Existing neural rendering approaches suffer from distorted material recovery and low relighting fidelity, primarily because they rely on simplified BRDF models or coupled diffuse/specular parameterizations. This paper proposes a decoupled relightable reconstruction framework: it introduces a microfacet-based BRDF with explicit glossiness parameterization; leverages diffusion priors to guide normal and diffuse albedo estimation; and integrates deferred shading with coarse-to-fine environment map optimization to enhance high-dynamic-range specular modeling. By employing 2D Gaussian rasterization, differentiable joint optimization, and physically consistent material decomposition, our method achieves high-fidelity geometry and material reconstruction in complex glossy scenes. Experiments demonstrate that our approach produces more realistic and consistent relighting under novel lighting conditions, significantly improving both visual fidelity and physical plausibility.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Feature Construction/Reformulation
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Accurate reconstruction and relighting of glossy objects remain a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing neural rendering approaches often rely on simplified BRDF models or parameterizations that couple diffuse and specular components, which restricts faithful material recovery and limits relighting fidelity. We propose a relightable framework that integrates a microfacet BRDF with the specular-glossiness parameterization into 2D Gaussian Splatting with deferred shading. This formulation enables more physically consistent material decomposition, while diffusion-based priors for surface normals and diffuse color guide early-stage optimization and mitigate ambiguity. A coarse-to-fine optimization of the environment map accelerates convergence and preserves high-dynamic-range specular reflections. Extensive experiments on complex, glossy scenes demonstrate that our method achieves high-quality geometry and material reconstruction, delivering substantially more realistic and consistent relighting under novel illumination compared to existing Gaussian splatting methods.

Problem

• Disentangling shape, material and illumination for glossy objects
• Overcoming limitations of simplified BRDF models in neural rendering
• Achieving physically consistent material decomposition for relighting

Innovation

• Integrates microfacet BRDF with specular-glossiness parameterization into Gaussian Splatting
• Uses diffusion-based priors for surface normals and diffuse color
• Applies coarse-to-fine optimization of environment map for specular reflections