PAM-ToD：面向跨时段3D高斯溅射的即插即用外观建模

中文摘要 AI 辅助

将预训练的3D高斯溅射（3DGS）道路场景适配到新的时段，需要从少量锚定图像中学习外观变化，同时保持一致的实时渲染。我们提出PAM-ToD，这是一种轻量级插件，在固定预训练3DGS参数的同时学习颜色校正。PAM-ToD缩放每个高斯的现有颜色以建模光照变化，并使用附加项处理额外亮度，例如夜间路灯开启时的情况。在简化的图像形成模型下，源和目标外观之间的关系可消除不变的表面反照率，使我们无需单独估计反照率和光照即可学习这些校正。该模型校正场景中的颜色，同时允许校正随位置和高斯变化。为了从少量锚定图像中指导学习，它抑制这些校正的空间突变。我们还引入CARLA-ToD基准，该基准在三个时段具有匹配的几何结构、相机位姿和移动物体轨迹。每个插件使用少量目标时段锚定图像进行训练，而单独的视图用于评估。在静态和动态设置下，即使锚定图像来自多相机的单次同步捕获，PAM-ToD也比基线实现更高的峰值信噪比（PSNR）和更低的学习感知图像块相似度（LPIPS）。

英文摘要

Adapting a pre-trained 3D Gaussian Splatting (3DGS) road scene to a new time of day requires learning appearance changes from a few anchor images while preserving consistent, real-time rendering. We propose PAM-ToD, a lightweight plug-in that learns color corrections while keeping the pre-trained 3DGS parameters fixed. PAM-ToD scales each Gaussian's existing color to model illumination changes and uses an additive term for additional brightness, such as when street lamps turn on at night. Under a simplified image formation model, unchanged surface albedo can be eliminated from the relation between source and target appearances, allowing us to learn these corrections without separately estimating albedo and illumination. The model corrects colors across the scene while allowing the corrections to vary by location and by Gaussian. To guide learning from a few anchor images, it discourages abrupt spatial changes in these corrections. We also introduce CARLA-ToD, a benchmark with matching geometry, camera poses, and moving-object trajectories across three times of day. A few target-time anchor images are used to train each plug-in, while separate views are used for evaluation. Across the static and dynamic settings, PAM-ToD achieves higher PSNR and lower LPIPS than the baselines, even when the anchor images come from a single synchronized capture across multiple cameras.

发表机构

• Chubu University（中部大学）
• Elith Inc.（Elith公司）
• DGIST（大邱庆北科学技术院）
• KAIST（韩国科学技术院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

21 pages, 9 figures