Metraipolis › archive › dc_e8ba06fe75cb
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing — arXiv:2608.29269
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29269
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:58:53.934Z
- SHA-256 of the archived text
96c366f730f7de447f878853151944c6f3f8e2bb48987b9014dd1209089218ac- Stable URL of this page
https://metraipolis.com/documento/dc_e8ba06fe75cb
How to cite
LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing — arXiv:2608.29269 — arXiv (en), https://arxiv.org/abs/2608.29269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8ba06fe75cb (Metraipolis archive dc_e8ba06fe75cb, sha256 96c366f730f7de447f878853151944c6f3f8e2bb48987b9014dd1209089218ac)
BibTeX
@misc{dce8ba06fe75cb,
title = {LightFuse: Relightable Interactive Gaussian Scene Reconstruction via Multi-Scan Fusion and 2D Gaussian Ray Tracing — arXiv:2608.29269},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29269},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8ba06fe75cb; sha256 96c366f730f7de447f878853151944c6f3f8e2bb48987b9014dd1209089218ac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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: this https URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29269 — 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 2026-10-17T09:28:48.017Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).