探索带形变的 6D 物体位姿估计
Exploring 6D Object Pose Estimation with Deformation
为 6D 位姿估计提供了首个系统性的形变物体基准：26 类物体各含 1 个标准态与 3 个形变态的高精度 3D 扫描及到标准网格的配准，可直接用于评测现有位姿方法在非刚性形变下的失效程度，也可作为形变鲁棒位姿估计的训练与测试源。
原文依据 performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 DeSOPE，一个面向 6DoF 形变物体的大规模数据集。大多数 6D 物体位姿方法假设物体是刚性或铰接的，而这一假设在实际中并不成立，因为物体由于磨损、撞击或形变会偏离其标准形状。为对这种情况建模，我们引入 DeSOPE 数据集，它对 26 个常见物体类别提供了高保真三维扫描，每个类别均采集一个标准状态和三种形变配置，并带有到标准网格的精确三维配准。此外，该数据集还包含一个 RGB-D 数据集，覆盖多种场景，共 133K 帧，并通过半自动流水线生成 665K 条位姿标注。我们首先为每个实例标注二维掩码，然后使用一种物体位姿方法计算初始位姿，再通过物体级 SLAM 系统对其进行优化，最后进行人工校验以生成最终标注。我们评估了若干物体位姿方法，发现随着形变程度增加，性能急剧下降，这表明稳健地处理此类形变对实际应用至关重要。项目主页与数据集见 https://desope-6d.github.io/。
英文原文摘要 1155 字符
We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or deformation. To model this, we introduce the DeSOPE dataset, which features high-fidelity 3D scans of 26 common object categories, each captured in one canonical state and three deformed configurations, with accurate 3D registration to the canonical mesh. Additionally, it features an RGB-D dataset with 133K frames across diverse scenarios and 665K pose annotations produced via a semi-automatic pipeline. We begin by annotating 2D masks for each instance, then compute initial poses using an object pose method, refine them through an object-level SLAM system, and finally perform manual verification to produce the final annotations. We evaluate several object pose methods and find that performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical for practical applications. The project page and dataset are available at https://desope-6d.github.io/.