OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jia, Yupeng, He, Jie, Chen, Runze, Zhao, Fang, Luo, Haiyong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929347385884672
author Jia, Yupeng
He, Jie
Chen, Runze
Zhao, Fang
Luo, Haiyong
author_facet Jia, Yupeng
He, Jie
Chen, Runze
Zhao, Fang
Luo, Haiyong
contents Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational resources than BEV or 2D methods. We propose a novel 3D semantic occupancy perception method, OccupancyDETR, which utilizes a DETR-like object detection, a mixed dense-sparse 3D occupancy decoder. Our approach distinguishes between foreground and background within a scene. Initially, foreground objects are detected using the DETR-like object detection. Subsequently, queries for both foreground and background objects are fed into the mixed dense-sparse 3D occupancy decoder, performing upsampling in dense and sparse methods, respectively. Finally, a MaskFormer is utilized to infer the semantics of the background voxels. Our approach strikes a balance between efficiency and accuracy, achieving faster inference times, lower resource consumption, and improved performance for small object detection. We demonstrate the effectiveness of our proposed method on the SemanticKITTI dataset, showcasing an mIoU of 14 and a processing speed of 10 FPS, thereby presenting a promising solution for real-time 3D semantic occupancy perception.
format Preprint
id arxiv_https___arxiv_org_abs_2309_08504
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction
Jia, Yupeng
He, Jie
Chen, Runze
Zhao, Fang
Luo, Haiyong
Robotics
Computer Vision and Pattern Recognition
Visual-based 3D semantic occupancy perception is a key technology for robotics, including autonomous vehicles, offering an enhanced understanding of the environment by 3D. This approach, however, typically requires more computational resources than BEV or 2D methods. We propose a novel 3D semantic occupancy perception method, OccupancyDETR, which utilizes a DETR-like object detection, a mixed dense-sparse 3D occupancy decoder. Our approach distinguishes between foreground and background within a scene. Initially, foreground objects are detected using the DETR-like object detection. Subsequently, queries for both foreground and background objects are fed into the mixed dense-sparse 3D occupancy decoder, performing upsampling in dense and sparse methods, respectively. Finally, a MaskFormer is utilized to infer the semantics of the background voxels. Our approach strikes a balance between efficiency and accuracy, achieving faster inference times, lower resource consumption, and improved performance for small object detection. We demonstrate the effectiveness of our proposed method on the SemanticKITTI dataset, showcasing an mIoU of 14 and a processing speed of 10 FPS, thereby presenting a promising solution for real-time 3D semantic occupancy perception.
title OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.08504