用3D高斯点云检测物体移动，无需深度图或预设模型。
3DGS-CD: 3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement
- 基于3DGS与EfficientSAM，通过对比不同时刻图像检测变化。
- 仅需1张新图，18秒内完成检测，准确率高出14%。
- 适合机器人重置、场景重建等实时应用，代码开源。
我们提出3DGS-CD，首个基于3D高斯溅射（3DGS）的物理物体重排检测方法。该方法通过比较不同时刻采集的未对齐图像，估计3D物体级变化。利用3DGS的新型视图渲染能力和EfficientSAM的零样本分割能力，检测2D物体级变化，并在多视角间关联融合，生成3D变化掩码与物体变换。本方法仅需最少一张后变更图像，可在18秒内准确识别杂乱环境中的变化，且不依赖深度输入、用户指令、预定义物体类别或物体模型——只要物体发生重排即被识别。在公开与自采的真实数据集上评估，相比当前最优的辐射场基方法，准确率提升最高达14%，速度加快三个数量级。这一显著性能提升支持多种下游应用，包括物体重建、机器人工作区重置和3DGS模型更新。代码与数据将开源于https://github.com/520xyxyzq/3DGS-CD。
原文摘要 · Abstract (English)
We present 3DGS-CD, the first 3D Gaussian Splatting (3DGS)-based method for detecting physical object rearrangements in 3D scenes. Our approach estimates 3D object-level changes by comparing two sets of unaligned images taken at different times. Leveraging 3DGS's novel view rendering and EfficientSAM's zero-shot segmentation capabilities, we detect 2D object-level changes, which are then associated and fused across views to estimate 3D change masks and object transformations. Our method can accurately identify changes in cluttered environments using sparse (as few as one) post-change images within as little as 18s. It does not rely on depth input, user instructions, pre-defined object classes, or object models -- An object is recognized simply if it has been re-arranged. Our approach is evaluated on both public and self-collected real-world datasets, achieving up to 14% higher accuracy and three orders of magnitude faster performance compared to the state-of-the-art radiance-field-based change detection method. This significant performance boost enables a broad range of downstream applications, where we highlight three key use cases: object reconstruction, robot workspace reset, and 3DGS model update. Our code and data will be made available at https://github.com/520xyxyzq/3DGS-CD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。