Metraipolis › archive › dc_68b2dd277e9b

GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats — arXiv:2611.05593

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05593
License (as archived)
CC0-1.0
Archived
2026-11-05T18:22:33.639Z
SHA-256 of the archived text
1b2280292406364f0402cf1261cd97155a2f9a6b1177d07669c8030c49b6eb46
Stable URL of this page
https://metraipolis.com/documento/dc_68b2dd277e9b

How to cite

GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats — arXiv:2611.05593 — arXiv (en), https://arxiv.org/abs/2611.05593 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68b2dd277e9b (Metraipolis archive dc_68b2dd277e9b, sha256 1b2280292406364f0402cf1261cd97155a2f9a6b1177d07669c8030c49b6eb46)
BibTeX
@misc{dc68b2dd277e9b,
  title = {GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats — arXiv:2611.05593},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05593},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68b2dd277e9b; sha256 1b2280292406364f0402cf1261cd97155a2f9a6b1177d07669c8030c49b6eb46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05593. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Can a neural network learn to render 3D Gaussian splats on its own, with no rasterizer in the renderer? We present GaussianRenderFormer, a transformer that takes a set of Gaussians and a camera and outputs the image directly. Each Gaussian becomes one token in a view-independent encoder, and a view-dependent decoder turns small patches of camera rays into pixels by attending to those tokens. Trained on 26,820 Objaverse objects pruned to 20,000 Gaussians each, GaussianRenderFormer renders 300 unseen objects at 38.08 dB PSNR against the full, unpruned splats, while rasterizing the same pruned input reaches 44.02 dB. The gap is not one of generalization, and our diagnostics are consistent with a bottleneck in the view decoder: telling it the projected footprint of each Gaussian, which it could in principle infer, adds 1.4 dB. Under-training is not ruled out. Code, trained models and videos: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05593 — 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 2026-11-05T18:15:49.032Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).