解决大运动下3D点云场景插值难题，实现平滑过渡。
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
- 学习全局映射场，将点云对齐到统一参考空间。
- 在大运动场景下性能显著优于现有方法。
- 支持外推，适用于传统方法失效的极端运动。
现有动态场景插值方法通常假设相邻时间步之间的运动较小，可由局部线性模型近似。实际中，即使轻微偏离此假设也会导致传统技术失效。本文提出全局运动对应器（GMC），一种新方法，能稳健处理大运动并实现平滑过渡。GMC学习预测SE(3)映射的一元势场，将点云映射到共享的规范空间，同时平衡对应关系、空间与语义平滑性及局部刚性。实验表明，在两个状态发生大范围全局运动时，该方法显著优于现有基线模型。此外，其具备外推能力，而其他基线方法无法实现。
原文摘要 · Abstract (English)
Existing dynamic scene interpolation methods typically assume that the motion between consecutive timesteps is small enough so that displacements can be locally approximated by linear models. In practice, even slight deviations from this small-motion assumption can cause conventional techniques to fail. In this paper, we introduce Global Motion Corresponder (GMC), a novel approach that robustly handles large motion and achieves smooth transitions. GMC learns unary potential fields that predict SE(3) mappings into a shared canonical space, balancing correspondence, spatial and semantic smoothness, and local rigidity. We demonstrate that our method significantly outperforms existing baselines on 3D scene interpolation when the two states undergo large global motions. Furthermore, our method enables extrapolation capabilities where other baseline methods cannot.
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。