开放词汇物体6D姿态估计
Open-vocabulary object 6D pose estimation
AI总结：
提出开放词汇物体6D姿态估计新设置，仅凭文本提示在双RGBD视角下分割并估计相对6D姿态，通过融合物体级信息与局部特征实现泛化，在REAL275和Toyota-Light基准上超越现有方法。
摘要：
我们引入了开放词汇物体6D姿态估计的新设置，其中使用文本提示来指定感兴趣的物体。与现有方法相比，在我们的设置中，(i) 感兴趣的物体仅通过文本提示指定，(ii) 推理时不需要物体模型（例如CAD或视频序列），(iii) 物体从不同场景的两个RGBD视角成像。为了在这种设置下工作，我们提出了一种新颖的方法，利用视觉-语言模型从场景中分割感兴趣的物体并估计其相对6D姿态。我们方法的关键在于一种精心设计的策略，将提示提供的物体级信息与局部图像特征融合，从而产生一个能够泛化到新概念的特征空间。我们在基于两个流行数据集REAL275和Toyota-Light的新基准上验证了我们的方法，这两个数据集共同涵盖了出现在四千个图像对中的34个物体实例。结果表明，我们的方法在估计不同场景中物体的相对6D姿态方面，优于一种成熟的手工方法以及一种最新的基于深度学习的基线方法。代码和数据集可在 https://jcorsetti.github.io/oryon 获取。
英文摘要：
We introduce the new setting of open-vocabulary object 6D pose estimation, in which a textual prompt is used to specify the object of interest. In contrast to existing approaches, in our setting (i) the object of interest is specified solely through the textual prompt, (ii) no object model (e.g., CAD or video sequence) is required at inference, and (iii) the object is imaged from two RGBD viewpoints of different scenes. To operate in this setting, we introduce a novel approach that leverages a Vision-Language Model to segment the object of interest from the scenes and to estimate its relative 6D pose. The key of our approach is a carefully devised strategy to fuse object-level information provided by the prompt with local image features, resulting in a feature space that can generalize to novel concepts. We validate our approach on a new benchmark based on two popular datasets, REAL275 and Toyota-Light, which collectively encompass 34 object instances appearing in four thousand image pairs. The results demonstrate that our approach outperforms both a well-established hand-crafted method and a recent deep learning-based baseline in estimating the relative 6D pose of objects in different scenes. Code and dataset are available at https://jcorsetti.github.io/oryon.
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。
