仅用一张图就能准确估计物体姿态，且无需3D模型或大量训练数据。
Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
- 通过扩散模型生成多视角图像，双向匹配实现姿态估计。
- 在合成与真实数据集上均优于现有方法，视角变化下仍保持稳定性能。
- 适合快速部署到新物体，尤其适用于缺乏3D模型的场景。
本文提出一种新型通用单视图物体姿态估计方法，仅需一张RGB图像即可确定物体姿态。与依赖实例级姿态估计并需大量训练数据的传统方法不同，本方法无需3D物体模型或多个视角图像，仅需一个参考图像即可泛化至未见过的物体。该特性通过扩散模型生成新视角图像，并在生成图像上进行双向匹配实现。定量实验表明，该方法在合成与真实数据集上均优于现有技术，尤其在显著视角变化条件下仍表现出强鲁棒性与通用性。代码将发布于 https://github.com/scy639/Gen2SM。
原文摘要 · Abstract (English)
In this paper, we present a novel generalizable object pose estimation method to determine the object pose using only one RGB image. Unlike traditional approaches that rely on instance-level object pose estimation and necessitate extensive training data, our method offers generalization to unseen objects without extensive training, operates with a single reference image of the object, and eliminates the need for 3D object models or multiple views of the object. These characteristics are achieved by utilizing a diffusion model to generate novel-view images and conducting a two-sided matching on these generated images. Quantitative experiments demonstrate the superiority of our method over existing pose estimation techniques across both synthetic and real-world datasets. Remarkably, our approach maintains strong performance even in scenarios with significant viewpoint changes, highlighting its robustness and versatility in challenging conditions. The code will be re leased at https://github.com/scy639/Gen2SM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。