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

2026-01-30

AI Summary

Existing radiance field–based methods for indoor scene reconstruction struggle to support editing due to baked lighting and the absence of explicit light transport, while mesh-based inverse rendering approaches impose stringent geometric accuracy requirements that hinder their applicability to real-world scenes. This work proposes a novel method that integrates 2D Gaussian representations with path tracing, introducing 2D Gaussians as mesh-free, light-transport-friendly geometric proxies for the first time. By unifying geometric representation and explicitly decoupling emissive from non-emissive components, our approach separates reconstruction from rendering. It enables efficient single-bounce optimization and high-quality multi-bounce path tracing, achieving finer reconstruction details and physically consistent, natural editing results in both synthetic and real indoor scenes, effectively avoiding mesh artifacts and baked lighting limitations.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Computational Photography, Image & Video Synthesis
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Recent reconstruction methods based on radiance field such as NeRF and 3DGS reproduce indoor scenes with high visual fidelity, but break down under scene editing due to baked illumination and the lack of explicit light transport. In contrast, physically based inverse rendering relies on mesh representations and path tracing, which enforce correct light transport but place strong requirements on geometric fidelity, becoming a practical bottleneck for real indoor scenes. In this work, we propose Emission-Aware Gaussians and Path Tracing (EAG-PT), aiming for physically based light transport with a unified 2D Gaussian representation. Our design is based on three cores: (1) using 2D Gaussians as a unified scene representation and transport-friendly geometry proxy that avoids reconstructed mesh, (2) explicitly separating emissive and non-emissive components during reconstruction for further scene editing, and (3) decoupling reconstruction from final rendering by using efficient single-bounce optimization and high-quality multi-bounce path tracing after scene editing. Experiments on synthetic and real indoor scenes show that EAG-PT produces more natural and physically consistent renders after editing than radiant scene reconstructions, while preserving finer geometric detail and avoiding mesh-induced artifacts compared to mesh-based inverse path tracing. These results suggest promising directions for future use in interior design, XR content creation, and embodied AI.

Problem

• indoor scene reconstruction
• scene editing
• light transport
• physically based rendering
• mesh representation

Innovation

• Emission-Aware Gaussians
• Path Tracing
• Scene Editing
• Unified Gaussian Representation
• Physically Based Rendering