GS-Pose：基于3D高斯溅射的可泛化分割式6D物体姿态估计
GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting
AI总结：
本文提出GS-Pose统一框架，通过分阶段采用不同物体表示，结合3D高斯溅射优化6D物体姿态估计，在两个数据集上达到当前最优性能，支持用普通设备采集新物体。
摘要：
本文提出GS-Pose，一种用于定位并估计新物体6D姿态的统一框架。GS-Pose首先获取一组已知姿态的、针对未见过物体的RGB图像，构建三种不同的表示并存入数据库。推理时，GS-Pose按顺序运行：在输入图像中定位物体，用检索方法估计初始6D姿态，再用渲染对比方法优化姿态。核心思路是在流程各阶段使用合适的物体表示。尤其在优化步骤，我们利用3D Gaussian splatting（3D高斯溅射），这是一种新型可微渲染技术，渲染速度快且优化时间相对较短。现成工具链和消费级硬件（如手机）可用于捕获待加入数据库的新物体。在LINEMOD和OnePose-LowTexture数据集上的大量评估表明其性能优异，创下了新的state-of-the-art（当前最优水平）。项目页面：https://dingdingcai.github.io/gs-pose。
英文摘要：
This paper introduces GS-Pose, a unified framework for localizing and estimating the 6D pose of novel objects. GS-Pose begins with a set of posed RGB images of a previously unseen object and builds three distinct representations stored in a database. At inference, GS-Pose operates sequentially by locating the object in the input image, estimating its initial 6D pose using a retrieval approach, and refining the pose with a render-and-compare method. The key insight is the application of the appropriate object representation at each stage of the process. In particular, for the refinement step, we leverage 3D Gaussian splatting, a novel differentiable rendering technique that offers high rendering speed and relatively low optimization time. Off-the-shelf toolchains and commodity hardware, such as mobile phones, can be used to capture new objects to be added to the database. Extensive evaluations on the LINEMOD and OnePose-LowTexture datasets demonstrate excellent performance, establishing the new state-of-the-art. Project page: https://dingdingcai.github.io/gs-pose.
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。
