面向稀疏视图的单目6D位姿估计的目标高斯方法
Object Gaussian for Monocular 6D Pose Estimation from Sparse Views
AI总结：
本文提出SGPose框架，利用三维高斯泼溅在仅约十个稀疏视图和随机初始化条件下回归稠密2D-3D对应关系，摆脱对CAD模型和SfM几何的依赖，在Occlusion LM-O等基准上超越现有方法。
摘要：
单目目标位姿估计作为计算机视觉和机器人领域的核心任务，高度依赖精确的2D-3D对应关系，而这些对应关系通常需要昂贵的CAD模型，且这些模型可能并不容易获得。目标三维重建方法提供了一种替代方案，其中三维高斯泼溅（3D Gaussian Splatting，3DGS）的最新进展展现出引人注目的潜力。然而，其性能仍然受到影响，并且在输入视图较少时容易过拟合。针对这一挑战，我们提出了SGPose，这是一个利用基于高斯的方法进行稀疏视图目标位姿估计的新颖框架。仅需少至十个视图，SGPose通过随机长方体初始化生成几何感知表示，摆脱了对传统3DGS方法所需的运动恢复结构（Structure-from-Motion，SfM）流程导出几何的依赖。SGPose通过在稀疏输入和随机初始化条件下回归图像与重建模型之间的稠密2D-3D对应关系，消除了对CAD模型的依赖，而几何一致的深度监督和在线合成视图变形是成功的关键。在典型基准上的实验，尤其是在Occlusion LM-O数据集上的实验表明，即使在稀疏视图约束下，SGPose也优于现有方法，凸显了其在实际应用中的潜力。
英文摘要：
Monocular object pose estimation, as a pivotal task in computer vision and robotics, heavily depends on accurate 2D-3D correspondences, which often demand costly CAD models that may not be readily available. Object 3D reconstruction methods offer an alternative, among which recent advancements in 3D Gaussian Splatting (3DGS) afford a compelling potential. Yet its performance still suffers and tends to overfit with fewer input views. Embracing this challenge, we introduce SGPose, a novel framework for sparse view object pose estimation using Gaussian-based methods. Given as few as ten views, SGPose generates a geometric-aware representation by starting with a random cuboid initialization, eschewing reliance on Structure-from-Motion (SfM) pipeline-derived geometry as required by traditional 3DGS methods. SGPose removes the dependence on CAD models by regressing dense 2D-3D correspondences between images and the reconstructed model from sparse input and random initialization, while the geometric-consistent depth supervision and online synthetic view warping are key to the success. Experiments on typical benchmarks, especially on the Occlusion LM-O dataset, demonstrate that SGPose outperforms existing methods even under sparse view constraints, under-scoring its potential in real-world 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。
