SOURCE-LINKED INTELLIGENCE

RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global