EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

TL;DR

EAG-PT introduces a novel method for reconstructing and rendering indoor scenes that balances physical accuracy and editability by using Gaussian representations and path tracing, outperforming existing radiance-field and mesh-based methods.

Contribution

The paper proposes a unified Gaussian-based approach for scene reconstruction and rendering that enables physically consistent editing and high-quality visualization of indoor environments.

Findings

EAG-PT achieves more natural and physically consistent edited renderings.

It preserves finer geometric details and avoids mesh artifacts.

The method outperforms existing radiance-field and mesh-based inverse path tracing techniques.

Abstract

Recent radiance-field-based reconstruction methods, such as NeRF and 3DGS, achieve high visual fidelity for indoor scenes, but often break down under scene editing due to baked illumination and the lack of explicit light transport. In contrast, inverse path tracing methods based on mesh representations enforce correct light transport but require highly accurate geometry, making them difficult to apply robustly to real indoor scenes. We present Emission-Aware Gaussians and Path Tracing (EAG-PT), a method for physically based reconstruction and rendering of indoor scenes using a unified 2D Gaussian representation, targeting editable diffuse global illumination. Our approach consists of three key ideas: (1) representing indoor scenes with 2D Gaussians as a transport-friendly geometric proxy that avoids explicit mesh reconstruction; (2) explicitly separating emissive and non-emissive components during reconstruction to support editing; and (3) decoupling reconstruction from final rendering by using efficient single-bounce optimization and high-quality multi-bounce path tracing, respectively. Experiments on synthetic and real indoor scenes show that EAG-PT produces more natural and physically consistent edited renderings than radiance-field reconstructions, while preserving finer geometric detail and avoiding mesh-induced artifacts compared with mesh-based inverse path tracing. These results highlight the potential of our approach for applications such as interior design, XR content creation, and embodied AI.