面向泛化性相对物体位姿估计的3D感知假设与验证
3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
AI总结:
针对仅单参考视图的未见物体相对位姿估计难题,提出带3D感知验证的假设-验证框架,在多个数据集上实现了更优精度与大幅位姿变化下的鲁棒性。
摘要:
现有解决泛化性物体位姿估计问题的方法高度依赖获取未见物体的密集视图。与之不同,我们针对仅能获取物体单个参考视图的场景展开研究,目标是估计该参考视图与一张呈现物体不同位姿的查询图像之间的相对物体位姿。该场景下,由于测试时存在未见物体,且参考视图与查询图像间存在大幅物体位姿变化,因此鲁棒的泛化能力至关重要。为此,我们提出一种全新的假设-验证框架,该框架生成并评估多个位姿假设,最终选取最可靠的假设作为相对物体位姿。为衡量可靠性,我们引入3D感知验证机制,该机制对从两张输入图像中学习到的3D物体表示显式施加3D变换。我们在Objaverse、LINEMOD和CO3D数据集上开展的综合实验表明,在处理未见物体时,我们的方法在相对位姿估计方面具备更优的精度,且在大幅位姿变化下具有鲁棒性。
英文摘要:
Prior methods that tackle the problem of generalizable object pose estimation highly rely on having dense views of the unseen object. By contrast, we address the scenario where only a single reference view of the object is available. Our goal then is to estimate the relative object pose between this reference view and a query image that depicts the object in a different pose. In this scenario, robust generalization is imperative due to the presence of unseen objects during testing and the large-scale object pose variation between the reference and the query. To this end, we present a new hypothesis-and-verification framework, in which we generate and evaluate multiple pose hypotheses, ultimately selecting the most reliable one as the relative object pose. To measure reliability, we introduce a 3D-aware verification that explicitly applies 3D transformations to the 3D object representations learned from the two input images. Our comprehensive experiments on the Objaverse, LINEMOD, and CO3D datasets evidence the superior accuracy of our approach in relative pose estimation and its robustness in large-scale pose variations, when dealing with unseen objects.
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。