LightHarmony3D：在3D高斯散射场景中和谐光照与阴影以实现物体插入
LightHarmony3D: Harmonizing Illumination and Shadows for Object Insertion in 3D Gaussian Splatting
AI总结：
本文提出LightHarmony3D框架，通过生成模块预测HDR环境映射，实现光照一致的物体插入，提升3D高斯散射场景的光照和阴影真实性。
摘要：
3D高斯散射（3DGS）能够实现高保真的场景几何和外观重建。在此基础上，将外部网格物体插入到重建的3DGS场景中，可实现交互式编辑和内容增强，应用于AR/VR、虚拟布景和数字内容创作。然而，实现网格插入的物理一致光照和阴影仍具挑战性，因为需要准确的场景照明估计和多视角一致的渲染。为解决这一挑战，我们提出了LightHarmony3D，一种新的用于3DGS场景中光照一致的网格插入框架。我们的方法核心是所提出的生成模块，通过单次正向传递预测插入位置的完整360°HDR环境映射。通过利用生成先验而非迭代优化，我们的方法高效地捕捉主导场景照明，并在保持多视角一致性的同时实现物理基础的着色和阴影。此外，我们引入了首个专门针对3DGS中网格插入的基准，提供标准化评估框架以评估光照一致性和逼真度。在多个真实世界重建数据集上的广泛实验表明，LightHarmony3D在真实感和多视角一致性方面达到了最先进的水平。
英文摘要：
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° 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
