PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments

Yang You, Kai Xiong, Zhening Yang, Zhengxiang Huang, Junwei Zhou +5 more
12/23/2023
cs.CV

Official code: qq456cvb/PACE (34 stars, MIT, last commit 2025-09-13).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

qq456cvb/PACEOfficial100%
MIT
341Shell, MATLAB1 years agoMIT
dataseteccv2024pose-estimation

Similar Papers

Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

88% match1 repo1362024

Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects

87% match1 repo12026

DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios

87% match2025

CAD-Estate: Large-scale CAD Model Annotation in RGB Videos

87% match1 repo1282023

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

85% match2025

Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation

85% match1 repo162024

Cite this paper

@article{you2023pace,
  title  = {PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments},
  author = {Yang You and Kai Xiong and Zhening Yang and Zhengxiang Huang and Junwei Zhou and Ruoxi Shi and Zhou Fang and Adam W. Harley and Leonidas Guibas and Cewu Lu},
  year   = {2023},
  eprint = {2312.15130},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.15130v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.15130.svg)](https://codeofpaper.com/paper/2312.15130)

Discussion