发表机构
Indraprastha Institute of Information Technology, Delhi; Dolby Laboratories（德里印度信息技术学院; 杜比实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Ad-Relight，一种仅推理的扩散重打光方法，通过分离阴影与结构并探测预训练模型，实现广告图形场景光照迁移，在560个放置中优于基线，尤其改善非均匀光照下的地板图形。
AI 中文摘要
在广播帧中替换可见广告在几何上是直接的，但在光度上是精细的。粘贴的图形即使具有正确的透视，当其亮度、阴影或遮蔽与下方表面不一致时，仍可能显得脱离。本文提出Ad-Relight，一种仅推理的程序，用于将场景光照迁移到提供的广告图形，而无需收集特定于横幅的训练集。该程序首先将缓慢变化的阴影与图形结构分离，然后使用两个几乎相同的背景探测预训练的扩散重打光器，以隔离目标区域的贡献。最后一步将此残差与平滑的亮度场和软衰减掩码相结合。在560个生成的放置中，该方法在结构相似性、感知距离和光照一致性方面优于几何合成和直接重打光基线。人工判断和自动化偏好研究表明，在具有非均匀光照的地板安装图形上收益最明显。当前研究基于图像；时间稳定性仍是一个开放的扩展方向。
英文摘要
Replacing a visible advertisement in a broadcast frame is geometrically straightforward but photometrically delicate. A pasted graphic can have the correct perspective and still appear detached when its brightness, shading, or shadow disagrees with the surface beneath it. This paper presents Ad-Relight, an inference-only procedure for transferring scene illumination to a supplied advertising graphic without collecting a banner-specific training set. The procedure first separates slowly varying shade from graphic structure, then probes a pretrained diffusion relighter with two nearly identical backgrounds to isolate the contribution of the target region. A final pass combines this residual with a smoothed luminance field and a soft attenuation mask. Across 560 generated placements, the approach improves structural similarity, perceptual distance, and illumination agreement over geometric compositing and direct relighting baselines. Human judgments and an automated preference study show the clearest gains on floor-mounted graphics with nonuniform lighting. The current study is image based; temporal stabilization remains an open extension.
Comments5 pages, 5 figures, and 3 tables; conference-style computer vision manuscript focused on single-frame advertising-banner relighting
