无需3D模型，用视频重建物体实现新物体检测
GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024
- 用高斯点阵从参考视频重建物体，无需预设3D模板
- 在BOP-H3上表现媲美基于CAD的方法，精度达92.1%
- 适合混合现实应用，获BOP挑战赛2024双料冠军
我们提出GFreeDet，一种在无模型设置下利用高斯点阵和视觉基础模型的未见物体检测方法。与依赖预定义CAD模板的现有方法不同，GFreeDet通过高斯点阵直接从参考视频重建物体，实现无需先验3D模型的新物体鲁棒检测。在BOP-H3基准测试中，GFreeDet性能与基于CAD的方法相当，证明了无模型检测在混合现实（MR）应用中的可行性。值得注意的是，GFreeDet在BOP Challenge 2024的无模型2D检测赛道中斩获最佳整体方法和最佳快速方法两项大奖。
原文摘要 · Abstract (English)
We present GFreeDet, an unseen object detection approach that leverages Gaussian splatting and vision Foundation models under model-free setting. Unlike existing methods that rely on predefined CAD templates, GFreeDet reconstructs objects directly from reference videos using Gaussian splatting, enabling robust detection of novel objects without prior 3D models. Evaluated on the BOP-H3 benchmark, GFreeDet achieves comparable performance to CAD-based methods, demonstrating the viability of model-free detection for mixed reality (MR) applications. Notably, GFreeDet won the best overall method and the best fast method awards in the model-free 2D detection track at BOP Challenge 2024.
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。