GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets

2026-09-17

AI Summary

为解决Gaussian Splatting中光照与几何紧耦合问题，GS-PI通过3D点云上的条件扩散过程生成PBR材质，实现多视图一致性并避免光照伪影。

Abstract

Gaussian Splatting (GS) excels at novel-view synthesis but encodes baked-in radiance, tightly entangling illumination with geometry and preventing seamless integration into physically based rendering (PBR) pipelines. Existing inverse-rendering methods attempt to disentangle materials via joint optimization, but often suffer from competing objectives that cause severe ambiguities and residual lighting artifacts. To overcome this, we present GS-PI, a novel optimization-decoupled framework that casts PBR material generation as a geometry-conditioned diffusion process on 3D point clouds. By operating directly in the 3D domain, our method inherently guarantees multi-view consistency, sidestepping the severe pixel correspondence issues that challenge 2D diffusion approaches. We introduce a multi-scale cross-view conditioning mechanism that integrates three complementary components: a global semantic prior, source-anchored photometric cues, and an absolute spatial learned view-direction conditioning signal. This design efficiently compresses complex multi-view evidence, mitigating cross-view projection misalignment and successfully preventing specular highlights from baking into intrinsic colors. By extracting a point cloud from a pre-trained Gaussian model, predicting PBR attributes via conditional diffusion, and distilling them back through differentiable rasterisation, we yield a fully relightable PBR-GS asset. GS-PI outperforms recent inverse-rendering baselines while replacing per-scene joint illumination/BRDF optimization with a learned diffusion pass followed by a short target-driven distillation, without requiring proxy meshes.

Problem

• Gaussian Splatting
• Physically Based Rendering
• Inverse Rendering

Innovation

• Optimization-Decoupled
• PBR Material Generation
• Geometry-Conditioned Diffusion
• Multi-Scale Cross-View Conditioning
• Gaussian Splatting