Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: You, Yang, Xiong, Kai, Yang, Zhening, Huang, Zhengxiang, Zhou, Junwei, Shi, Ruoxi, Fang, Zhou, Harley, Adam W., Guibas, Leonidas, Lu, Cewu
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.15130
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910535241433088
author You, Yang
Xiong, Kai
Yang, Zhening
Huang, Zhengxiang
Zhou, Junwei
Shi, Ruoxi
Fang, Zhou
Harley, Adam W.
Guibas, Leonidas
Lu, Cewu
author_facet You, Yang
Xiong, Kai
Yang, Zhening
Huang, Zhengxiang
Zhou, Junwei
Shi, Ruoxi
Fang, Zhou
Harley, Adam W.
Guibas, Leonidas
Lu, Cewu
contents We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale benchmark designed to advance the development and evaluation of pose estimation methods in cluttered scenarios. PACE provides a large-scale real-world benchmark for both instance-level and category-level settings. The benchmark consists of 55K frames with 258K annotations across 300 videos, covering 238 objects from 43 categories and featuring a mix of rigid and articulated items in cluttered scenes. To annotate the real-world data efficiently, we develop an innovative annotation system with a calibrated 3-camera setup. Additionally, we offer PACE-Sim, which contains 100K photo-realistic simulated frames with 2.4M annotations across 931 objects. We test state-of-the-art algorithms in PACE along two tracks: pose estimation, and object pose tracking, revealing the benchmark's challenges and research opportunities. Our benchmark code and data is available on https://github.com/qq456cvb/PACE.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15130
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments
You, Yang
Xiong, Kai
Yang, Zhening
Huang, Zhengxiang
Zhou, Junwei
Shi, Ruoxi
Fang, Zhou
Harley, Adam W.
Guibas, Leonidas
Lu, Cewu
Computer Vision and Pattern Recognition
We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale benchmark designed to advance the development and evaluation of pose estimation methods in cluttered scenarios. PACE provides a large-scale real-world benchmark for both instance-level and category-level settings. The benchmark consists of 55K frames with 258K annotations across 300 videos, covering 238 objects from 43 categories and featuring a mix of rigid and articulated items in cluttered scenes. To annotate the real-world data efficiently, we develop an innovative annotation system with a calibrated 3-camera setup. Additionally, we offer PACE-Sim, which contains 100K photo-realistic simulated frames with 2.4M annotations across 931 objects. We test state-of-the-art algorithms in PACE along two tracks: pose estimation, and object pose tracking, revealing the benchmark's challenges and research opportunities. Our benchmark code and data is available on https://github.com/qq456cvb/PACE.
title PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.15130