发表机构
QUT Centre for Robotics; ARIAM Hub（昆士兰科技大学机器人中心; ARIAM 研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出PlenoCI特征，基于3DGS全光场导数高效检测视图依赖变化，在CL-Splats上mIoU提升25.7%，误报减少两个数量级，并实现几何/外观变化分类。
AI 中文摘要
辐射场表示（如3D高斯泼溅，3DGS）天然编码了诸如遮挡和视图依赖性等复杂视觉现象，但它们本质上约束不足。独立优化的重建即使在未变化的区域也会收敛到不同的基元配置。我们引入了全光特征（PlenoCI），这是一种基于这些表示所近似的全光场构建的新型特征。PlenoCI直接捕获丰富的视觉行为，同时忽略朗伯纹理。通过从3DGS表示推导出闭式解析全光导数，我们高效地检测这些5D结构。我们的方法在构造上对约束不足的表示具有鲁棒性，在未变化场景的独立重建之间报告的误报数量比同期工作少两个数量级。我们展示了PlenoCI在变化分类中的实用性。首先，我们使用实例感知的3DGS流程检测变化，在CL-Splats上取得了最先进的结果，相比最强竞争对手mIoU提高了25.7%，同时在更具挑战性的PASLCD基准上保持竞争力。利用PlenoCI，我们将变化分类为几何或外观变化，平衡准确率为0.735，与最佳基线相当。我们相信全光导数和PlenoCI为视觉复杂环境中的视图依赖性理解开辟了新方向。代码和数据可在以下网址获取：https URL。
英文摘要
Radiance field representations such as 3D Gaussian Splatting (3DGS) natively encode complex visual phenomena such as occlusions and view dependence, but they are inherently underconstrained. Independently optimized reconstructions converge to different primitive configurations, even in unchanged regions. We introduce Plenoptic CharacterIstics (PlenoCI), a novel feature built from the plenoptic field these representations approximate. PlenoCI directly captures rich visual behaviors while ignoring Lambertian textures. By deriving closed-form analytic plenoptic derivatives from a 3DGS representation, we efficiently detect these 5D structures. Our approach is robust to underconstrained representations by construction, reporting two orders of magnitude fewer false positives between independent reconstructions of unchanged scenes than concurrent work. We demonstrate PlenoCI's utility on change classification. First, we detect changes with an instance-aware 3DGS pipeline, achieving state-of-the-art results on CL-Splats with a 25.7% mIoU gain over the strongest competitor, while remaining competitive on the more challenging PASLCD benchmark. Leveraging PlenoCI, we classify changes as geometric or appearance-based with a balanced accuracy of 0.735, comparable to the best performing baseline. We believe plenoptic derivatives and PlenoCI open new directions for view dependence aware understanding in visually complex environments. Code and data are available at https://js0n-lai.github.io/plenoci.
Comments15 pages, 9 figures
