paper-with-me

홈 › Papers

OnePose: One-Shot Object Pose Estimation without CAD Models

2022-05-24 · CVPR 2022 1 · Jiaming Sun, ZiHao Wang, Siyu Zhang, Xingyi He, Hongcheng Zhao, Guofeng Zhang, Xiaowei Zhou

We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, OnePose does not rely on CAD models and can handle objects in arbitrary categories without instance- or category-specific network training. OnePose draws the idea from visual localization and only requires a simple RGB video scan of the object to build a sparse SfM model of the object. Then, this model is registered to new query images with a generic feature matching network. To mitigate the slow runtime of existing visual localization methods, we propose a new graph attention network that directly matches 2D interest points in the query image with the 3D points in the SfM model, resulting in efficient and robust pose estimation. Combined with a feature-based pose tracker, OnePose is able to stably detect and track 6D poses of everyday household objects in real-time. We also collected a large-scale dataset that consists of 450 sequences of 150 objects.

📄 PDF Abstract BibTeX arXiv:2205.12257

Code (1)

zju3dv/OnePose 공식 구현 pytorch

Tasks

6D Pose EstimationGraph AttentionObjectPose EstimationVisual Localization

Similar Papers 제목 키워드 기반

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

2023-01-18 · Xingyi He, Jiaming Sun, Yuang Wang, Di Huang 외

We propose a new method for object pose estimation without CAD models. The previous feature-matching-based method OnePose has shown promising results under a one-shot setting which eliminates the need for CAD models or o…

Keypoint DetectionObjectPose Estimation

One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation

2025-09-09 · Zheng Geng, Nan Wang, Shaocong Xu, Chongjie Ye 외 arxiv

Estimating the 6D pose of arbitrary unseen objects from a single reference image is critical for robotics operating in the long-tail of real-world instances. However, this setting is notoriously challenging: 3D models ar…

6D Pose Estimation3D Generation

DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss

2020-08-20 · Georgios Albanis, Nikolaos Zioulis, Anastasios Dimou, Dimitrios Zarpalas 외

In this work we consider UAVs as cooperative agents supporting human users in their operations. In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial i…

3D Pose EstimationDrone Pose EstimationPose Estimation

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference

2023-05-25 · Zhiwen Fan, Panwang Pan, Peihao Wang, Yifan Jiang 외

Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. Thes…

3D geometryObjectPose Estimation

Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images

2023-06-13 · Panwang Pan, Zhiwen Fan, Brandon Y. Feng, Peihao Wang 외

The accurate estimation of six degrees-of-freedom (6DoF) object poses is essential for many applications in robotics and augmented reality. However, existing methods for 6DoF pose estimation often depend on CAD templates…

object-detectionObject DetectionPose Estimation