让3D场景可重布光、可编辑，支持物体移动与材质修改。
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing
- 通过多视角融合重建共享背景与可动物体
- 实现物理级重布光，平均提升9.74dB PSNR
- 适合需要真实光影交互的虚拟场景设计
可重布光的交互式场景重建旨在从不同摆放状态的扫描数据中构建可编辑的3D模型，并在新光照条件下渲染新布局。现有方法或把光照烘焙进外观，或仅对固定场景恢复材质与光照，导致编辑后布局阴影和间接光照不一致。我们提出LightFuse，一种基于2D高斯的框架，实现了显式的材质-光照解耦与物理驱动的重布光。LightFuse首先跨状态融合观测，重建共享背景与可动物体；随后通过面向光线追踪的几何优化，生成更完整且一致的表面。在优化后的几何上，采用分阶段可微一跳光线追踪训练，分离出共享的金属度-粗糙度材质与状态相关的环境光照。最终场景支持物体重排、材质编辑与重布光，每次交互后通过光线追踪重新计算外观。在合成场景上的实验表明，其重布光质量达到当前最优，平均优于最强基线9.74 dB PSNR与0.121 SSIM。项目页：https://zhn202.github.io/LightFuse/
原文摘要 · Abstract (English)
Relightable interactive scene reconstruction aims to build an editable 3D model from scans of different object arrangements and render new layouts under novel illumination. Existing methods either bake lighting into appearance or recover material and illumination only for fixed scenes, leaving edited layouts with inconsistent shadows and indirect lighting. We present LightFuse, a 2D Gaussian framework that extends interactive scene reconstruction with explicit material-illumination decomposition and physically based relighting. LightFuse first fuses observations across states to reconstruct a shared background and movable objects. It then conducts ray-tracing-oriented geometry refinement to produce more complete and consistent surfaces. On the refined geometry, staged training with differentiable one-bounce ray tracing separates shared metallic--roughness material from state-specific environment lighting. The resulting scene supports object rearrangement, material editing, and relighting, while ray tracing recomputes appearance after each interaction. Experiments across synthetic scenes demonstrate state-of-the-art relighting quality, outperforming the strongest baseline by +9.74\,dB PSNR and +0.121 SSIM on average. Project page: https://zhn202.github.io/LightFuse/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。