外观
论文arXiv 2610.1837415 天前
SchemaPose：基于 RGB 的带参数化类别图式的类别级姿态估计
原文链接：SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema（arXiv 2610.18374 · 发布日期：2026-10-13）
SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema
SchemaPose面向RGB类别级9D姿态估计，采用显式参数化类别图式与查询式端到端框架，在合成和真实数据上验证。
核心要点
- RGB单目类别级估计需泛化到未见实例，并联合推断平移、旋转和尺寸。
- 方法以显式参数化图式建模类别共性和结构化实例差异。
- 推断的图式变量在端到端查询式框架中指导姿态相关预测。
- 合成和真实数据实验显示，其在RGB类别级9D姿态估计中达到SOTA。
验证范围与局限：验证范围为合成和真实数据上的RGB类别级9D姿态估计。
英文摘要 (Abstract)
RGB-based category-level 9D pose estimation remains highly challenging because a monocular system must generalize across unseen object instances while jointly inferring 3D translation, 3D rotation, and 3D size. Unlike instance-level pose estimation, the category-level setting requires the network to learn both what is shared across objects within a category and how individual instances vary in structure. This challenge is amplified in the RGB-only setting, where pose cues, category-level commonality, and instance-specific variation are entangled in appearance without direct geometric constraints, making it difficult for existing frameworks to learn a representation that is truly aligned with the category-level estimation objective. To address this problem, we propose SchemaPose, a schema-guided framework for RGB-based category-level pose estimation. SchemaPose equips the estimation pipeline with an explicit parametric schema for modeling category-level regularities together with structured instance variation, and uses the inferred schema variables to guide pose-related prediction in an end-to-end query-based framework. The same formulation also supports template instantiation, synthetic annotation, and pose learning within a unified framework. Experiments on synthetic and real data show that SchemaPose achieves state-of-the-art performance among RGB-based methods for category-level 9D pose estimation.
作者：Shuang Wu, Jiude Wei, Cewu Lu, Jianhua Sun
来源
本页事实对应的公开页面，以原文为准。