跳到主要导航 跳到搜索 跳到主要内容

GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction

  • Tianhao Li
  • , Yang Li
  • , Mengtian Li
  • , Yisheng Deng
  • , Weifeng Ge*
  • *此作品的通讯作者
  • Fudan University
  • Shanghai University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Accurately perceiving dynamic environments is a fundamental task for autonomous driving and robotic systems. Existing methods inadequately utilize temporal information, relying mainly on local temporal interactions between adjacent frames and failing to leverage global sequence information effectively. To address this limitation, we investigate how to effectively aggregate global temporal features from temporal sequences, aiming to achieve occupancy representations that efficiently utilize global temporal information from historical observations. For this purpose, we propose a global temporal aggregation denoising network named GTAD, introducing a global temporal information aggregation framework as a new paradigm for holistic 3D scene understanding. Our method employs an in-model latent denoising network to aggregate local temporal features from the current moment and global temporal features from historical sequences. This approach enables the effective perception of both fine-grained temporal information from adjacent frames and global temporal patterns from historical observations. As a result, it provides a more coherent and comprehensive understanding of the environment. Extensive experiments on the nuScenes and Occ3D-nuScenes benchmark and ablation studies demonstrate the superiority of our method.

源语言英语
主期刊名IROS 2025 - 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, Conference Proceedings
编辑Christian Laugier, Alessandro Renzaglia, Nikolay Atanasov, Stan Birchfield, Grzegorz Cielniak, Leonardo De Mattos, Laura Fiorini, Philippe Giguere, Kenji Hashimoto, Javier Ibanez-Guzman, Tetsushi Kamegawa, Jinoh Lee, Giuseppe Loianno, Kevin Luck, Hisataka Maruyama, Philippe Martinet, Hadi Moradi, Urbano Nunes, Julien Pettre, Alberto Pretto, Tommaso Ranzani, Arne Ronnau, Silvia Rossi, Elliott Rouse, Fabio Ruggiero, Olivier Simonin, Danwei Wang, Ming Yang, Eiichi Yoshida, Huijing Zhao
出版商Institute of Electrical and Electronics Engineers Inc.
4075-4082
页数8
ISBN(电子版)9798331543938
DOI
出版状态已出版 - 2025
活动2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2025 - Hangzhou, 中国
期限: 19 10月 202525 10月 2025

出版系列

姓名IEEE International Conference on Intelligent Robots and Systems
ISSN(印刷版)2153-0858
ISSN(电子版)2153-0866

会议

会议2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2025
国家/地区中国
Hangzhou
时期19/10/2525/10/25

学术指纹

探究 'GTAD: Global Temporal Aggregation Denoising Learning for 3D Semantic Occupancy Prediction' 的科研主题。它们共同构成独一无二的学术指纹。

引用此