RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives

• 类型：arxiv
• 标识：2609.05738
• 链接：https://arxiv.org/abs/2609.05738
• 主分类：engineering
• 形态：method
• TLDR：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
• 待LLM分类：否
• 标题中文：RenderFormer-V2：基于异构场景基元的神经渲染
• TLDR中文：我们提出 RenderFormer-V2，一个统一的基于 transformer 的学习型神经渲染模型，可与现代基于物理的渲染系统互补，无需逐场景训练或专用代码，即可处理焦散、体积散射、环境光照、带纹理与置换的表面以及分布外材质等多种光传输效果。RenderFormer-V2 将全局光传输建模为序列到序列变换。沿袭前作，它仍采用两阶段流程：先是与视图无关的阶段，解析场景内基元到……
• 来源文件：
• /inbox/tom/_candidates/2026-09-10-agent-rag-longcontext-candidates.json