LumiTokens: 3D Relighting via Token-Space Lighting Transformation

LumiTokens：通过标记空间光照变换实现 3D 重光照

Existing 3D relighting methods operate through either explicit material decomposition, diffusion-based view-space generation, or a combination of both, requiring full recomputation for each new lighting condition. 现有的 3D 重光照方法通常通过显式材质分解、基于扩散的视图空间生成，或两者的结合来实现，这要求针对每种新的光照条件进行完整的重新计算。

We observe that recent latent scene representations, which encode multi-view images into a set of compact tokens with no fixed physical semantics, open up a novel design space for relighting. 我们观察到，近期的潜在场景表示（latent scene representations）将多视图图像编码为一组没有固定物理语义的紧凑标记（tokens），这为重光照开辟了一个全新的设计空间。

We present LumiTokens, a framework that formulates 3D relighting as a direct transformation on latent scene tokens, without explicit 3D representations, rendering equations, or physics-based decomposition. 我们提出了 LumiTokens，这是一个将 3D 重光照表述为对潜在场景标记直接变换的框架，无需显式的 3D 表示、渲染方程或基于物理的分解。

Our model introduces a Scene Token Editor that processes scene tokens jointly with light-ray tokens through self-attention, producing updated tokens that can be decoded into multi-view-consistent relit images. 我们的模型引入了一个场景标记编辑器（Scene Token Editor），通过自注意力机制将场景标记与光线标记（light-ray tokens）联合处理，生成更新后的标记，这些标记可以解码为多视图一致的重光照图像。

To support diverse lighting types through a unified interface, all lighting signals, including environment maps, point lights, and area lights, are parameterized as Plucker ray tokens, enabling native 3D user interaction with a representation that carries no explicit spatial structure. 为了通过统一接口支持多种光照类型，所有光照信号（包括环境贴图、点光源和面光源）都被参数化为 Plucker 射线标记，从而使得用户能够以一种不携带显式空间结构的方式进行原生的 3D 交互。

Crucially, this design supports progressive relighting: because the editor’s output remains in the same latent space as its input, a user can incrementally build up illumination one light source at a time, with each edit composing in token space. 至关重要的是，该设计支持渐进式重光照：由于编辑器的输出与输入处于相同的潜在空间，用户可以一次添加一个光源来逐步构建光照，且每次编辑都在标记空间中进行组合。

Experiments demonstrate that LumiTokens achieves comparable or superior relighting quality to other methods and supports progressive, composable lighting edits. 实验表明，LumiTokens 在重光照质量上达到了与其他方法相当甚至更优的效果，并支持渐进式、可组合的光照编辑。