Metraipolis › archive › dc_f30cdc145c02

EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation — arXiv:2610.01876

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01876
License (as archived)
CC0-1.0
Archived
2026-10-06T19:14:45.921Z
SHA-256 of the archived text
11251a798e056994eeef640c544124606b12f7101ac85e7cb72e6802c5c3d5e8
Stable URL of this page
https://metraipolis.com/documento/dc_f30cdc145c02

How to cite

EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation — arXiv:2610.01876 — arXiv (en), https://arxiv.org/abs/2610.01876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f30cdc145c02 (Metraipolis archive dc_f30cdc145c02, sha256 11251a798e056994eeef640c544124606b12f7101ac85e7cb72e6802c5c3d5e8)
BibTeX
@misc{dcf30cdc145c02,
  title = {EvenSplat: Coupled 2D-3D Decomposition for Gaussian Splatting under Exposure and Illumination Variation — arXiv:2610.01876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f30cdc145c02; sha256 11251a798e056994eeef640c544124606b12f7101ac85e7cb72e6802c5c3d5e8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A surface photographed under even light presents nearly the same appearance from every angle; the same surface under uneven light does not. Exposure changes between views, illumination varies within a single image, and locally strong light sources leave one region bright and its neighbor in shadow. Multi-view reconstruction methods such as 3D Gaussian Splatting treat these lighting artifacts as if they were properties of the scene, entangling capture-specific illumination with the geometry and color they recover. We present EvenSplat, a framework that separates the two. EvenSplat couples an image-space illumination decomposition with an illumination field carried by the Gaussians, so that the same explanation of the lighting is shared between the two-dimensional and three-dimensional views of the scene; a camera-response network and a local exposure-compensation module absorb the global and residual differences that remain across training images. Through extensive experiments across multiple datasets and diverse forms of uneven illumination (cross-view exposure, spatial illumination variation, and high-contrast lighting) on both real-world captured and simulated benchmarks, EvenSplat generally outperforms state-of-the-art methods, particularly under high-contrast illumination.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01876 — 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 2026-10-06T17:37:36.849Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).