论文标题
融合了基于检索的3D方向估计未见对象的局部相似性
Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects
论文作者
论文摘要
在本文中，我们解决了从单眼图像估算以前未见对象的3D方向的任务。该任务与大多数现有深度学习方法所考虑的任务形成对比，后者通常认为在训练过程中已经观察到测试对象。为了处理看不见的对象，我们遵循基于检索的策略，并通过计算查询图像和合成生成的参考图像之间的多尺度局部相似性来防止网络学习特定于对象的特征。然后，我们引入了一个自适应融合模块，该模块可稳健地将局部相似性汇总到成对图像的全局相似性评分中。此外，我们通过制定快速检索策略来加快检索过程。我们在LineMod，LineMod-Occluded和T-less数据集上进行的实验表明，我们的方法比以前的作品产生的概括更大。我们的代码和预训练模型可在https://sailor-z.github.io/projects/unseen_object_pose.html上找到。
In this paper, we tackle the task of estimating the 3D orientation of previously-unseen objects from monocular images. This task contrasts with the one considered by most existing deep learning methods which typically assume that the testing objects have been observed during training. To handle the unseen objects, we follow a retrieval-based strategy and prevent the network from learning object-specific features by computing multi-scale local similarities between the query image and synthetically-generated reference images. We then introduce an adaptive fusion module that robustly aggregates the local similarities into a global similarity score of pairwise images. Furthermore, we speed up the retrieval process by developing a fast retrieval strategy. Our experiments on the LineMOD, LineMOD-Occluded, and T-LESS datasets show that our method yields a significantly better generalization to unseen objects than previous works. Our code and pre-trained models are available at https://sailor-z.github.io/projects/Unseen_Object_Pose.html.
