arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07360cs.CVcs.AIcs.LG
收藏

基于关键点预测的目标姿态估计的自监督学习

Self-supervised learning of object pose estimation using keypoint prediction

University of Linköping(林雪平大学);University of Waterloo(滑铁卢大学)

Zahra Gharaee, Felix Järemo Lawin, Per-Erik Forssén

摘要:

本文介绍了最近的发展,在特定的目标姿态和形状预测从单一的图像。的主要贡献是一个新的方法来预测摄像机姿态的自监督学习的关键点对应的位置上的类别特定的变形形状。我们设计了一个网络来从分布在特定类别的平均形状上的一组关键点生成代理地面实况热图,其中每个关键点都由标记纹理上的唯一颜色表示。代理地面实况热图用于训练深度关键点预测网络,其可用于在线推理。与最先进的方法相比,所提出的相机姿态预测方法显示出显着的改进。我们的相机姿态预测方法用于从视频序列的2D图像帧在线推断3D对象。为了训练重建模型,它在每个训练步骤中仅接收来自视频序列的单个帧的轮廓掩模和类别特定的平均对象形状。我们使用代表鸟类类别的三个不同数据集进行了实验:CUB [51]图像数据集,YouTubeVos和Davis视频数据集。该网络在CUB数据集上进行训练,并在所有三个数据集上进行测试。使用在CUB训练集上训练的网络在YouTubeVos和Davis [56]视频序列上演示了在线实验。

英文摘要:

This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations on a category specific deformable shape. We designed a network to generate a proxy ground-truth heatmap from a set of keypoints distributed all over the category-specific mean shape, where each is represented by a unique color on a labeled texture. The proxy ground-truth heatmap is used to train a deep keypoint prediction network, which can be used in online inference. The proposed approach to camera pose prediction show significant improvements when compared with state-of-the-art methods. Our approach to camera pose prediction is used to infer 3D objects from 2D image frames of video sequences online. To train the reconstruction model, it receives only a silhouette mask from a single frame of a video sequence in every training step and a category-specific mean object shape. We conducted experiments using three different datasets representing the bird category: the CUB [51] image dataset, YouTubeVos and the Davis video datasets. The network is trained on the CUB dataset and tested on all three datasets. The online experiments are demonstrated on YouTubeVos and Davis [56] video sequences using a network trained on the CUB training set.

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。

↑