Generalist robot policies built upon 2D visual representations excel at semantic reasoning but inherently lack the explicit 3D spatial awareness required for high-precision tasks. Existing 3D integration methods struggle to bridge this gap due to the structural irregularity of sparse point clouds and the geometric distortion introduced by multi-view orthographic rendering. To overcome these barriers, we present ReMAP-DP, a novel framework synergizing standardized perspective reprojection with a structure-aware dual-stream diffusion policy. By coupling the re-projected views with pixel-aligned PointMaps, our dual-stream architecture leverages learnable modality embeddings to fuse frozen semantic features and explicit geometric descriptors, ensuring precise implicit patch-level alignment. Extensive experiments across simulation and real-world environments demonstrate ReMAP-DP's superior performance in diverse manipulation tasks. On RoboTwin 2.0, it attains a 59.3% average success rate, outperforming the DP3 baseline by +6.6%. On ManiSkill 3, our method yields a 28% improvement over DP3 on the geometrically challenging Stack Cube task. Furthermore, ReMAP-DP exhibits remarkable real-world robustness, executing high-precision and dynamic manipulations with superior data efficiency from only a handful of demonstrations. Project page is available at: https://icr-lab.github.io/ReMAP-DP/

翻译：基于二维视觉表征的通用机器人策略在语义推理方面表现出色，但其本质缺乏高精度任务所需的显式三维空间感知能力。现有三维集成方法因稀疏点云的结构不规则性以及多视角正交渲染引入的几何畸变，难以弥合这一鸿沟。为突破这些障碍，我们提出ReMAP-DP——一个将标准化透视重投影与结构感知双流扩散策略协同融合的新型框架。通过将重投影视角与像素对齐的点图耦合，我们的双流架构利用可学习的模态嵌入融合冻结的语义特征与显式几何描述符，确保精确的隐式块级对齐。在仿真与真实环境中的大量实验表明，ReMAP-DP在多种操作任务中展现出卓越性能。在RoboTwin 2.0基准上，其平均成功率达59.3%，较DP3基线提升+6.6%。在ManiSkill 3基准的几何挑战性任务Stack Cube中，本方法相较DP3实现28%的性能提升。此外，ReMAP-DP展现出显著的真实世界鲁棒性，仅需少量演示即可凭借优越的数据效率完成高精度动态操作。项目主页：https://icr-lab.github.io/ReMAP-DP/