Metraipolis › archive › dc_0df261bd3d8a

LUMEN: Geometry-Guided Diffusion Model for Spatially-Varying HDR Illumination Estimation — arXiv:2611.01823

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01823
License (as archived): CC0-1.0
Archived: 2026-11-03T11:41:41.565Z
SHA-256 of the archived text: 3f0700e20a83800dd7df67b75b91e1ba124458dee02cf97d2f423e624ab0891c
Stable URL of this page: https://metraipolis.com/documento/dc_0df261bd3d8a

How to cite

LUMEN: Geometry-Guided Diffusion Model for Spatially-Varying HDR Illumination Estimation — arXiv:2611.01823 — arXiv (en), https://arxiv.org/abs/2611.01823 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0df261bd3d8a (Metraipolis archive dc_0df261bd3d8a, sha256 3f0700e20a83800dd7df67b75b91e1ba124458dee02cf97d2f423e624ab0891c)

BibTeX

@misc{dc0df261bd3d8a,
  title = {LUMEN: Geometry-Guided Diffusion Model for Spatially-Varying HDR Illumination Estimation — arXiv:2611.01823},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01823},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0df261bd3d8a; sha256 3f0700e20a83800dd7df67b75b91e1ba124458dee02cf97d2f423e624ab0891c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01823. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating scene illumination from images is challenging as lighting is inherently spatially varying, depending on geometry, occlusion, and light sources. Existing methods incorporate geometric cues by deriving local environment maps or probe-based representations, but largely rely on regression or parametric models, resulting in over-smoothed lighting and limited realism. We revisit spatially-varying illumination estimation from a generative perspective and introduce LUMEN, a geometry-conditioned diffusion framework for synthesizing high-dynamic-range (HDR) environment maps at arbitrary spatial locations from single or multi-view images. Specifically, we reconstruct a coarse 3D scene from input images and render partial environment maps at arbitrary locations to encode visibility and spatial structure. These signals are fused with multi-view image features and fed into a diffusion transformer to generate full HDR environment maps. To train the model, we build a synthetic dataset of 700 indoor scenes with dense spatial supervision, including multi-view RGB images, depth, and HDR illumination at multiple sampled locations. This dataset enables the model to learn spatially consistent lighting distributions across diverse scenes. Extensive experiments demonstrate that LUMEN significantly improves visual fidelity and spatial coherence compared to prior approaches.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.01823 — 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 2026-11-03T11:06:37.516Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).