SunFaded：面向相机搭载主动光源暗场景的光照感知高斯泼溅
SunFaded: Illumination-Aware Gaussian Splatting for Dark Scenes with Camera-Mounted Active Lighting
针对相机搭载主动光源的暗场景，提出基于瓦片的着色方案与光照加权损失函数，将光照与场景本征外观显式分离，并利用几何先验模型提升重建精度，为暗光下的三维重建提供了可复用的光照解耦思路。
原文依据 we employ a tile-based shading scheme that operates directly on the rendered images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高斯泼溅已成为一种流行的三维表示技术，但在外观一致性方面仍存在困难，尤其是在需要主动照明（例如相机闪光灯或协同移动的光源）来采集可用图像的暗场景中，会导致剧烈的局部外观波动。现有方法主要针对野外场景的全局外观变化（如不同时段或天气条件引起的变化）进行建模，但无法处理带有移动光源的暗场景中存在的严重变化。本文提出一种新颖的基于高斯泼溅的方法，用于在主动光源刚性附着于相机并随之移动的暗场景中构建场景表示。在该框架内，我们引入一种光照加权损失函数，驱动表示趋向于底层无光照场景。此外，与先前工作中调整每个高斯的光照不同，我们采用基于瓦片的着色方案，直接作用于渲染图像，在显著降低计算成本的同时，显式地将光照与本征场景外观分离。另外，我们通过将恢复的无光照场景外观与先进的几何先验模型相结合，进一步细化学习到的高斯表示，显著提升了几何精度。实验结果表明，与最优技术相比，我们的方法在挑战性环境中实现了更优的重建质量。
英文原文摘要 1576 字符
Gaussian Splatting has emerged as a popular 3D representation technique, but still struggles with appearance inconsistencies, especially in dark scenes that require active illumination (e.g., camera flashes or co-moving light sources) to capture usable images, leading to dramatic local appearance fluctuations.While existing methods mainly focus on modeling global appearance changes for in-the-wild scenes, such as those caused by different times of day or weather conditions, they fail to handle the severe variations present in dark scenes with moving light sources.In this paper, we propose a novel Gaussian Splatting-based approach for constructing scene representations in dark scenes where active light sources are rigidly attached to the camera and move together with it.Within this framework, we introduce an illumination-weighted loss function that drives the representation toward the underlying unlit scene. Furthermore, instead of adjusting the illumination of each individual Gaussian as in prior work, we employ a tile-based shading scheme that operates directly on the rendered images, greatly reducing computational cost while explicitly separating illumination from intrinsic scene appearance.Additionally, we further refine the learned Gaussian representation by combining the recovered unlit scene appearance with an advanced geometric prior model, which significantly improves geometric accuracy.Experimental results demonstrate that our method achieves superior reconstruction quality in challenging environments compared to state-of-the-art techniques.