arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.19616cs.CV
收藏

UniPR: 一种统一的基于单立体对的物体级实拍到仿真感知与重建框架

UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair

NTU(国立新加坡大学);Tencent Robotics X(腾讯机器人实验室);Futian Laboratory(福田实验室);HKUST(香港科技大学);THU(清华大学)

Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu, Yonggen Ling, Yuxiao Yang, Ziwei Wang

AI总结:

本文提出UniPR,一种端到端的物体级实拍到仿真感知与重建框架,通过几何约束解决尺度模糊问题,消除了对类别特定规范的依赖,并通过大规模立体数据集LVS6D提升研究效率和实用性。

摘要:

从图像中感知和重建物体对于实拍到仿真转换任务至关重要,广泛应用于机器人领域。现有方法依赖多个子模块,如检测、分割、形状重建和姿态估计,但这种模块化流程存在效率低和累积误差的问题。为解决这些问题,我们提出了UniPR,这是首个端到端的物体级实拍到仿真感知与重建框架。UniPR直接在单个立体图像对上操作,利用几何约束解决尺度模糊问题。我们引入了姿态感知的形状表示,以消除对类别特定规范的依赖,并弥合重建与姿态估计任务之间的差距。此外,我们构建了一个大规模词汇立体数据集LVS6D,包含超过6,300个物体,以促进该领域的规模化研究。大量实验表明,UniPR在单次前向传递中并行重建场景中的所有物体,实现了显著的效率提升,并在多样化的物体类型中保持真实的物理比例,突显了其在实际机器人应用中的潜力。

英文摘要:

Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape reconstruction, and pose estimation to complete the pipeline. However, such modular pipelines suffer from inefficiency and cumulative error, as each stage operates on only partial or locally refined information while discarding global context. To address these limitations, we propose UniPR, the first end-to-end object-level real-to-sim perception and reconstruction framework. Operating directly on a single stereo image pair, UniPR leverages geometric constraints to resolve the scale ambiguity. We introduce Pose-Aware Shape Representation to eliminate the need for per-category canonical definitions and to bridge the gap between reconstruction and pose estimation tasks. Furthermore, we construct a large-vocabulary stereo dataset, LVS6D, comprising over 6,300 objects, to facilitate large-scale research in this area. Extensive experiments demonstrate that UniPR reconstructs all objects in a scene in parallel within a single forward pass, achieving significant efficiency gains and preserves true physical proportions across diverse object types, highlighting its potential for practical robotic applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑