Metraipolis › archive › dc_6602a428b1df
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives — arXiv:2609.05738
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05738
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:43.016Z
- SHA-256 of the archived text
4d4f6be1271efcc0ea6f0d41779b802aa62f2084c53db76bbf90ee31d7918975- Stable URL of this page
https://metraipolis.com/documento/dc_6602a428b1df
How to cite
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives — arXiv:2609.05738 — arXiv (en), https://arxiv.org/abs/2609.05738 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6602a428b1df (Metraipolis archive dc_6602a428b1df, sha256 4d4f6be1271efcc0ea6f0d41779b802aa62f2084c53db76bbf90ee31d7918975)
BibTeX
@misc{dc6602a428b1df,
title = {RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives — arXiv:2609.05738},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05738},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6602a428b1df; sha256 4d4f6be1271efcc0ea6f0d41779b802aa62f2084c53db76bbf90ee31d7918975},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05738. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, that can handle diverse light-transport effects such as caustics, volumetric scattering, environment lighting, textured and displaced surfaces and out-of-distribution materials without per-scene training or specialized code. RenderFormer-V2 models global light transport as a sequence-to-sequence transformation. Following its predecessor, RenderFormer-V2 also employs a two stage process: a view-independent stage that resolves intra-scene primitive to primitive transport, and a view-dependent stage that transforms the internal neural scene representation into image pixels. Different from RenderFormer, our model employs a novel combined windowed-attention and rendering-informed attention sink in the view-independent stage to improve scalability while maintaining render accuracy. To further improve versatility, RenderFormerV2 supports heterogeneous scene primitives, including environment maps and participating media, and it employs a material encoding independent of the underlying surface reflectance model that encodes material appearance via a novel neural embedding. We demonstrate the versatility of RenderFormer-V2 on a variety of scenes and perform an extensive ablation of the improved attention mechanism. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.05738 — 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 2026-10-16T13:39:43.127Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).