发表机构
University of Cape Town（开普敦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GS-Pool利用3DGS重建和SAM2掩码，通过摄影载体与蒸馏特征比较两次访问的高斯场，实现对象级变化检测，在PASLCD上显著超越现有方法。
AI 中文摘要
工厂、博物馆和测量员会相隔数月对同一空间进行拍摄，并需要知道哪些物体发生了变化。当每次访问都用三维高斯泼溅（3DGS）重建时，直接比较两次重建结果无法回答这个问题。训练是随机的，因此对未变化空间的两次重建永远不会重合，而且第二次访问通常是快速重扫描，照片数量要少得多。我们提出了GS-Pool，它接收同一空间的两个独立重建的高斯场，并返回每个场中发生变化的物体及其掩码。每次访问照片的SAM2掩码被提升到渲染它们的那些高斯上，并合并到一个对象池中，因此每个决策都是在三维中针对每个对象做出一次。我们引入了一种摄影载体，即每个输入重建相对于另一次访问照片的3DGS训练损失，该损失反向传播到渲染每个像素的高斯上。我们将其与GS-Diff的几何和颜色项以及我们蒸馏的DINOv3特征相结合。这些证据与两次访问中都存在的物体的证据进行比较，从而为每个场景设定一个变化阈值。在PASLCD上，GS-Pool达到了0.751/0.846的mIoU/F1分数，而最强的先前方法GS-Diff为0.644/0.758，提升了17%/12%。其mIoU也比O-SCD、PlenoCI和MV-3DCD分别高出36%、40%和57%，并在CL-Splats上达到0.855的mIoU，比MV-3DCD高出33%。每个发生变化的物体都作为一组高斯返回，并附带其决策背后的证据，检查员可以在三维中对其进行审查。
英文摘要
Factories, museums and surveyors photograph the same space months apart and need to know which objects changed. When each visit is reconstructed with 3D Gaussian Splatting (3DGS), a direct comparison of the two reconstructions does not answer this. Training is stochastic, so two reconstructions of an unchanged space never coincide, and the second visit is often a quick re-scan with far fewer photographs. We propose GS-Pool, which takes two independently reconstructed Gaussian fields of the same space and returns the changed objects in each, together with their masks. SAM2 masks of each visit's photographs are lifted onto the Gaussians that render them and merged into an object pool, so every decision is taken once per object in 3D. We introduce a photographic carrier, the 3DGS training loss of each input reconstruction against the other visit's photographs, backpropagated to the Gaussians that rendered each pixel. We combine it with GS-Diff's geometry and colour terms and our distilled DINOv3 features. This evidence is compared with that of the objects present in both visits, which sets a change threshold for each scene. On PASLCD, GS-Pool reaches mIoU/F1 scores of 0.751/0.846 against 0.644/0.758 for GS-Diff, the strongest prior method, a gain of 17%/12%. Its mIoU is also 36%, 40% and 57% above that of O-SCD, PlenoCI and MV-3DCD, and it reaches 0.855 mIoU on CL-Splats, 33% above MV-3DCD. Each changed object is returned as a set of Gaussians with the evidence behind its decision, which an inspector can review in 3D.
