Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

CoRR(2023)

引用 1|浏览10
暂无评分
摘要
Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range. In this paper, we propose a 6D object pose estimation method that can be trained with pure RGB images without any auxiliary information. We first obtain a rough pose initialization from networks trained on synthetic images rendered from the target's 3D mesh. Then, we introduce a refinement strategy leveraging the geometry constraint in synthetic-to-real image pairs from multiple different views. We formulate this geometry constraint as pixel-level flow consistency between the training images with dynamically generated pseudo labels. We evaluate our method on three challenging datasets and demonstrate that it outperforms state-of-the-art self-supervised methods significantly, with neither 2D annotations nor additional depth images.
更多
查看译文
关键词
pseudo flow consistency,self-supervised
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要