Metraipolis › archive › dc_2182afc6b8fa

LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting — arXiv:2609.02543

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02543
License (as archived)
CC0-1.0
Archived
2026-10-17T06:30:38.433Z
SHA-256 of the archived text
edff6d429e711bba4e49e078045de07aa0e8a74d40e716867d21b5ffbe244247
Stable URL of this page
https://metraipolis.com/documento/dc_2182afc6b8fa

How to cite

LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting — arXiv:2609.02543 — arXiv (en), https://arxiv.org/abs/2609.02543 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2182afc6b8fa (Metraipolis archive dc_2182afc6b8fa, sha256 edff6d429e711bba4e49e078045de07aa0e8a74d40e716867d21b5ffbe244247)
BibTeX
@misc{dc2182afc6b8fa,
  title = {LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting — arXiv:2609.02543},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02543},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2182afc6b8fa; sha256 edff6d429e711bba4e49e078045de07aa0e8a74d40e716867d21b5ffbe244247},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02543. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

3D Gaussian Splatting (3DGS) achieves high-quality, real-time novel view synthesis, but the resulting assets have baked-in illumination and cannot be easily relit. Inverse rendering methods optimize simplified reflectance and illumination models for each scene, limiting efficiency and relighting quality. Recent generative approaches leverage large diffusion models for realistic lighting edits, but applying them to 3DGS typically requires an additional per-scene optimization stage to bake the edited appearance into the representation. We present LightBridge, a feed-forward generative framework for controllable relighting of complete 3DGS assets in a single pass. To enable feed-forward training, we construct a large-scale Multi-Illumination Relighting Dataset with paired source and target observations of the same scenes. Latent Bridge Relighting Diffusion models relighting as source-to-target transport in latent space, enabling one-step extraction of 2D visual tokens without iterative diffusion sampling. A Gaussian Propagation Transformer uses a point transformer with sparse image-to-point self-attention followed by point-to-image cross-attention to efficiently propagate these cues across the complete 3DGS, while avoiding full attention over all image and Gaussian tokens. Experiments validate these designs, demonstrating competitive relighting quality and efficient single-pass prediction of complete relit 3DGS assets without scene-specific optimization. The code and dataset will be made publicly available upon acceptance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in eess.IV).
Categorie arXiv: Graphics (cs.GR) ; Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.02543 — 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 2026-10-17T06:14:34.690Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).