TrackOcc: Camera-based 4D Panoptic Occupancy Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhuoguang, Li, Kenan, Yang, Xiuyu, Jiang, Tao, Li, Yiming, Zhao, Hang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909534352572416
author Chen, Zhuoguang
Li, Kenan
Yang, Xiuyu
Jiang, Tao
Li, Yiming
Zhao, Hang
author_facet Chen, Zhuoguang
Li, Kenan
Yang, Xiuyu
Jiang, Tao
Li, Yiming
Zhao, Hang
contents Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial comprehensiveness or temporal consistency. In this work, we introduce a brand-new task, Camera-based 4D Panoptic Occupancy Tracking, which simultaneously addresses panoptic occupancy segmentation and object tracking from camera-only input. Furthermore, we propose TrackOcc, a cutting-edge approach that processes image inputs in a streaming, end-to-end manner with 4D panoptic queries to address the proposed task. Leveraging the localization-aware loss, TrackOcc enhances the accuracy of 4D panoptic occupancy tracking without bells and whistles. Experimental results demonstrate that our method achieves state-of-the-art performance on the Waymo dataset. The source code will be released at https://github.com/Tsinghua-MARS-Lab/TrackOcc.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08471
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TrackOcc: Camera-based 4D Panoptic Occupancy Tracking
Chen, Zhuoguang
Li, Kenan
Yang, Xiuyu
Jiang, Tao
Li, Yiming
Zhao, Hang
Computer Vision and Pattern Recognition
Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial comprehensiveness or temporal consistency. In this work, we introduce a brand-new task, Camera-based 4D Panoptic Occupancy Tracking, which simultaneously addresses panoptic occupancy segmentation and object tracking from camera-only input. Furthermore, we propose TrackOcc, a cutting-edge approach that processes image inputs in a streaming, end-to-end manner with 4D panoptic queries to address the proposed task. Leveraging the localization-aware loss, TrackOcc enhances the accuracy of 4D panoptic occupancy tracking without bells and whistles. Experimental results demonstrate that our method achieves state-of-the-art performance on the Waymo dataset. The source code will be released at https://github.com/Tsinghua-MARS-Lab/TrackOcc.
title TrackOcc: Camera-based 4D Panoptic Occupancy Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.08471