让人体新视角生成在不同光照下更真实、可编辑，且无需逐人优化。
Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis
- 用2D多视角图像直接预测3D高斯的几何、材质和光照信息，全程前向推理。
- 在多种光照下重建出精确深度和法向，支持带阴影和间接光的可编辑光影。
- 适合需要跨角色、跨光照泛化的人体3D生成场景，尤其看重真实感的项目。
我们提出GRGS，一种通用且可重照明的人体新视角生成3D高斯框架，能在多样光照条件下实现高保真重建。与依赖个体优化或忽略物理约束的现有方法不同，GRGS采用前馈式、全监督策略，将多视角2D观测中的几何、材质和光照线索投影至3D高斯表示。为在多变光照下恢复准确几何，引入基于合成重照明数据训练的光照鲁棒几何精修（LGR）模块，以预测精确深度与表面法线。基于高质量几何，进一步提出物理基础神经渲染（PGNR）模块，结合神经预测与物理着色模型，支持包含阴影与间接光照的可编辑重照明。此外，设计了从2D到3D的投影训练方案，利用环境遮蔽、直接光与间接光图的可微监督，降低光线追踪计算开销。大量实验表明，GRGS在视觉质量、几何一致性及跨角色、跨光照泛化能力上均优于现有方法。
原文摘要 · Abstract (English)
We propose GRGS, a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions. Unlike existing methods that rely on per-character optimization or ignore physical constraints, GRGS adopts a feed-forward, fully supervised strategy projecting geometry, material, and illumination cues from multi-view 2D observations into 3D Gaussian representations. To recover accurate geometry under diverse lighting conditions, we introduce a Lighting-robust Geometry Refinement (LGR) module trained on synthetically relit data to predict precise depth and surface normals. Based on the high-quality geometry, a Physically Grounded Neural Rendering (PGNR) module is further proposed to integrate neural prediction with physics-based shading, supporting editable relighting with shadows and indirect illumination. Moreover, we design a 2D-to-3D projection training scheme leveraging differentiable supervision from ambient occlusion, direct, and indirect lighting maps, alleviating the computational cost of ray tracing. Extensive experiments demonstrate that GRGS achieves superior visual quality, geometric consistency, and generalization across characters and lighting conditions.
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。