Metraipolis › archive › dc_ebef79789f4d

GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets — arXiv:2609.19907

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19907
License (as archived)
CC0-1.0
Archived
2026-10-10T05:05:36.865Z
SHA-256 of the archived text
603df77ff7fc2a0b02d51fcc07e2b165f6fb25e081798f91341a25172ec32b83
Stable URL of this page
https://metraipolis.com/documento/dc_ebef79789f4d

How to cite

GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets — arXiv:2609.19907 — arXiv (en), https://arxiv.org/abs/2609.19907 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebef79789f4d (Metraipolis archive dc_ebef79789f4d, sha256 603df77ff7fc2a0b02d51fcc07e2b165f6fb25e081798f91341a25172ec32b83)
BibTeX
@misc{dcebef79789f4d,
  title = {GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets — arXiv:2609.19907},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19907},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebef79789f4d; sha256 603df77ff7fc2a0b02d51fcc07e2b165f6fb25e081798f91341a25172ec32b83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19907. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.19907 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T04:26:09.558Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).