LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splatting
Tianyu Huang, Zhenyang Ren, Zhenchen Wan, Jiyang Zheng, Wenjie Wang, Runnan Chen, Mingming Gong, Tongliang Liu

TL;DR
LightHarmony3D introduces a fast, generative approach for physically consistent lighting and shadow rendering in 3D Gaussian Splatting scenes, enhancing realistic object insertion for AR/VR and content creation.
Contribution
It proposes a novel generative module for HDR environment map prediction that improves lighting consistency without iterative optimization.
Findings
Achieves state-of-the-art realism in object insertion scenes.
Provides a new benchmark for evaluating lighting and shadow consistency.
Demonstrates multi-view coherent and photorealistic results across datasets.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
