Metraipolis › archive › dc_97cbffc53007

RGBX-Next: Towards Realistic Generative Rendering from G-Buffers — arXiv:2608.13929

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.13929
License (as archived): CC0-1.0
Archived: 2026-10-19T04:02:16.991Z
SHA-256 of the archived text: b3170fcfae20b1a3426dabbf2cb21618d4434ff0615afbb13a23ba4d7dffb393
Stable URL of this page: https://metraipolis.com/documento/dc_97cbffc53007

How to cite

RGBX-Next: Towards Realistic Generative Rendering from G-Buffers — arXiv:2608.13929 — arXiv (en), https://arxiv.org/abs/2608.13929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97cbffc53007 (Metraipolis archive dc_97cbffc53007, sha256 b3170fcfae20b1a3426dabbf2cb21618d4434ff0615afbb13a23ba4d7dffb393)

BibTeX

@misc{dc97cbffc53007,
  title = {RGBX-Next: Towards Realistic Generative Rendering from G-Buffers — arXiv:2608.13929},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13929},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97cbffc53007; sha256 b3170fcfae20b1a3426dabbf2cb21618d4434ff0615afbb13a23ba4d7dffb393},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have achieved impressive results in image, video, and streaming generation. However, compared to traditional 3D rendering, they still lack precise control over the generated output. We believe a viable path forward is to use generative models as learned renderers conditioned on traditionally rendered G-buffers. We introduce RGBX-Next, a unified generative framework for forward and inverse rendering, which allows estimating G-buffers from images, videos, and streams, and rendering realistic images, videos, and streams from G-buffers. Our key contribution is a general recipe for finetuning diffusion transformer (DiT) models into generative forward and inverse renderers. We show that the resulting models achieve high quality in both realistic generative rendering and intrinsic decomposition. We will make all our models publicly available. We believe that the design principles presented in this paper will benefit future research on controllable generative forward and inverse rendering.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2608.13929 — 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 2026-10-19T03:57:57.843Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).