Automated 3D Dataset Generation for Arbitrary Objects

P. Schulz

doi:10.1109/ACCESS.2025.3617952

2025-01-01

PRE

P. Schulz

Thorsten Hempel

Ayoub Al-Hamadi

DOI：10.1109/ACCESS.2025.3617952

原文链接

原文求助

摘要

En 中文

6D位姿估计是各种自主系统（包括移动机器人和自动驾驶汽车）的基础，因为它能够实现无碰撞导航和物体抓取等基本能力。然而，训练高性能的位姿估计模型需要大规模且精确标注的数据集。由于捕获和标注过程复杂、昂贵且耗时，目前可用的3D数据集很少，且通常在类别多样性方面存在局限。为实践者提供能够生成任意物体3D数据集的工具，我们提出了一种端到端的数据集生成流水线，自动化了数据集生成的所有方面。通过利用Radiance Fields的隐式建模能力，我们的流水线能够构建高质量、任意复杂度的3D模型。这些3D模型作为合成数据集生成器的输入。对多个对象的全面评估表明，我们的流水线快速、易用且高度自动化。此外，我们还证明，在生成数据集上训练的位姿估计网络在典型应用场景中能够达到优异性能。

Keyword:

3D dataset generation

automation

3D modeling

3D detection

pose estimation neural rendering

期刊

IEEE Access

IF:

3.6

论文数:

9.8W

被引数:

29.4W

机构

otto-von-guericke-university magdeburg

学者数:

论文数: 31

被引数: 0

引用论文

IF0

PREAI

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

2019 International Conference on Robotics and Automation (ICRA)

IF0

2019-05-01

OAAI

Aayush Prakash; Shaad Boochoon; Mark Brophy; David Acuna; Eric Cameracci; Gavriel State; Omer Shapira; Stan Birchfield

Automating 3D Dataset Generation with Neural Radiance Fields

ROBOTICS, COMPUTER VISION AND INTELLIGENT SYSTEMS, ROBOVIS 2025

IF0

2026-01-01

PREAI

Schulz, Paul; Hempel, Thorsten; Al-Hamadi, Ayoub

Advances in Neural Rendering

Computer Graphics Forum

IF0

2022-05-24

OAAI

A. Tewari; J. Thies; B. Mildenhall; P. Srinivasan; E. Tretschk; W. Yifan; C. Lassner; V. Sitzmann; R. Martin‐Brualla; S. Lombardi; T. Simon; C. Theobalt; M. Nießner; J. T. Barron; G. Wetzstein; M. Zollhöfer; V. Golyanik

Monocular Vision and Machine Learning for Pose Estimation 单目视觉与机器学习在位姿估计中的应用

2023 IEEE/ION Position, Location and Navigation Symposium (PLANS)

IF0

2023-04-24

PREAI

Quang Tran; Jeffrey Choate; Clark N. Taylor; Scott Nykl; David Curtis

Pose estimation for non-cooperative spacecraft rendezvous using convolutional neural networks

2018 IEEE Aerospace Conference

IF0

2018-03-01

OAAI

Sumant Sharma; Connor Beierle; Simone D'Amico

Bacon: Band-limited Coordinate Networks for Multiscale Scene Representation

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2022-06-01

OAAI

David B. Lindell; Dave Van Veen; Jeong Joon Park; Gordon Wetzstein

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

IF0

2023-10-01

OAAI

Jiaxiang Tang; Hang Zhou; Xiaokang Chen; Tianshu Hu; Errui Ding; Jingdong Wang; Gang Zeng

A Sim-to-Real Object Recognition and Localization Framework for Industrial Robotic Bin Picking

IEEE Robotics and Automation Letters

IF0

2022-04-01

PREAI

Xianzhi Li; Rui Cao; Yidan Feng; Kai Chen; Biqi Yang; Chi-Wing Fu; Yichuan Li; Qi Dou; Yun-Hui Liu; Pheng-Ann Heng

Kubric: A scalable dataset generator

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2022-06-01

OAAI

Klaus Greff; Francois Belletti; Lucas Beyer; Carl Doersch; Yilun Du; Daniel Duckworth; David J Fleet; Dan Gnanapragasam; Florian Golemo; Charles Herrmann; Thomas Kipf; Abhijit Kundu; Dmitry Lagun; Issam Laradji; Hsueh-Ti Liu; Henning Meyer; Yishu Miao; Derek Nowrouzezahrai; Cengiz Oztireli; Etienne Pot; Noha Radwan; Daniel Rebain; Sara Sabour; Mehdi S. M. Sajjadi; Matan Sela; Vincent Sitzmann; Austin Stone; Deqing Sun; Suhani Vora; Ziyu Wang; Tianhao Wu; Kwang Moo Yi; Fangcheng Zhong; Andrea Tagliasacchi

查看更多内容