LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splatting

arXiv cs.CV / 4/1/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces LightHarmony3D, a framework designed to insert external mesh objects into 3D Gaussian Splatting (3DGS) scenes with physically consistent illumination and shadows.
LightHarmony3D uses a generative module that predicts a full 360° HDR environment map at the insertion point from a single forward pass, avoiding costly iterative illumination estimation.
The method is intended to preserve multi-view rendering consistency, enabling coherent shading/shadowing as the viewpoint changes.
The authors also propose the first dedicated benchmark for mesh insertion in 3DGS to standardize evaluation of lighting consistency and photorealism.
Experiments on multiple real-world reconstruction datasets reportedly show state-of-the-art realism and multi-view coherence compared with prior approaches.

Abstract

3D Gaussian Splatting (3DGS) enables high-fidelity reconstruction of scene geometry and appearance. Building on this capability, inserting external mesh objects into reconstructed 3DGS scenes enables interactive editing and content augmentation for immersive applications such as AR/VR, virtual staging, and digital content creation. However, achieving physically consistent lighting and shadows for mesh insertion remains challenging, as it requires accurate scene illumination estimation and multi-view consistent rendering. To address this challenge, we present LightHarmony3D, a novel framework for illumination-consistent mesh insertion in 3DGS scenes. Central to our approach is our proposed generative module that predicts a full 360{\deg} HDR environment map at the insertion location via a single forward pass. By leveraging generative priors instead of iterative optimization, our method efficiently captures dominant scene illumination and enables physically grounded shading and shadows for inserted meshes while maintaining multi-view coherence. Furthermore, we introduce the first dedicated benchmark for mesh insertion in 3DGS, providing a standardized evaluation framework for assessing lighting consistency and photorealism. Extensive experiments across multiple real-world reconstruction datasets demonstrate that LightHarmony3D achieves state-of-the-art realism and multi-view consistency.