← 返回时间线

paper

RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives

arXiv ↗
ID
2609.05738
分类
首次捕获
2026-09-10
状态
unread
作者
Chong Zeng, Yue Dong, Pieter Peers, Lvmin Zhang, Maneesh Agrawala
信号
🔥 2

信号历史

  • 2026-09-10HF Daily Papers · 🔥2
暂无信号数据

摘要

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.

我的笔记

还没有笔记。

在 GitHub 上写笔记 ↗(新建 content/notes/2609.05738.md,PR 合并后本页自动更新)