LightMover：带颜色与强度控制的生成式光照移动
LightMover: Generative Light Movement with Color and Intensity Controls
把光照编辑建模为视觉词元空间中的序列到序列预测，复用视频扩散先验，无需重新渲染即可改变光源位置、颜色与强度；其自适应词元剪枝（保留空间信息词元、压缩非空间属性）可迁移到其他基于词元的可控生成任务以缩短控制序列。
原文依据 We formulate light editing as a sequence-to-sequence prediction problem in visual token space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 LightMover，一个用于单张图像中可控光照操作的框架，它利用视频扩散先验，在不重新渲染场景的情况下产生物理上合理的光照变化。我们将光照编辑建模为视觉词元空间中的序列到序列预测问题：给定一张图像和光照控制词元，模型从单一视角同时调整光源位置、颜色与强度，以及由此产生的反射、阴影和衰减。这种对空间（移动）与外观（颜色、强度）控制的统一处理同时提升了对操作和光照的理解。我们进一步引入一种自适应词元剪枝机制，在紧凑编码非空间属性的同时保留具有空间信息的词元，将控制序列长度减少 41%，同时保持编辑保真度。为训练该框架，我们构建了一个可扩展的渲染管线，在不同光照位置、颜色和强度下生成大量图像对，同时保持场景内容与原始图像一致。LightMover 能够对光源位置、颜色和强度进行精确、独立的控制，并在不同任务上取得高峰值信噪比以及强语义一致性（DINO、CLIP）。
英文原文摘要 1269 字符
We present LightMover, a framework for controllable light manipulation in single images that leverages video diffusion priors to produce physically plausible illumination changes without re-rendering the scene. We formulate light editing as a sequence-to-sequence prediction problem in visual token space: given an image and light-control tokens, the model adjusts light position, color, and intensity together with resulting reflections, shadows, and falloff from a single view. This unified treatment of spatial (movement) and appearance (color, intensity) controls improves both manipulation and illumination understanding. We further introduce an adaptive token-pruning mechanism that preserves spatially informative tokens while compactly encoding non-spatial attributes, reducing control sequence length by 41% while maintaining editing fidelity. To train our framework, we construct a scalable rendering pipeline that generates large numbers of image pairs across varied light positions, colors, and intensities while keeping the scene content consistent with the original image. LightMover enables precise, independent control over light position, color, and intensity, and achieves high PSNR and strong semantic consistency (DINO, CLIP) across different tasks.