Polar Parametrization for Vision-based Surround-View 3D Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shaoyu, Wang, Xinggang, Cheng, Tianheng, Zhang, Qian, Huang, Chang, Liu, Wenyu
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917965186727936
author Chen, Shaoyu
Wang, Xinggang
Cheng, Tianheng
Zhang, Qian
Huang, Chang
Liu, Wenyu
author_facet Chen, Shaoyu
Wang, Xinggang
Cheng, Tianheng
Zhang, Qian
Huang, Chang
Liu, Wenyu
contents 3D detection based on surround-view camera system is a critical technique in autopilot. In this work, we present Polar Parametrization for 3D detection, which reformulates position parametrization, velocity decomposition, perception range, label assignment and loss function in polar coordinate system. Polar Parametrization establishes explicit associations between image patterns and prediction targets, exploiting the view symmetry of surround-view cameras as inductive bias to ease optimization and boost performance. Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR. PolarDETR achieves promising performance-speed trade-off on different backbone configurations. Besides, PolarDETR ranks 1st on the leaderboard of nuScenes benchmark in terms of both 3D detection and 3D tracking at the submission time (Mar. 4th, 2022). Code will be released at \url{https://github.com/hustvl/PolarDETR}.
format Preprint
id arxiv_https___arxiv_org_abs_2206_10965
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Polar Parametrization for Vision-based Surround-View 3D Detection
Chen, Shaoyu
Wang, Xinggang
Cheng, Tianheng
Zhang, Qian
Huang, Chang
Liu, Wenyu
Computer Vision and Pattern Recognition
3D detection based on surround-view camera system is a critical technique in autopilot. In this work, we present Polar Parametrization for 3D detection, which reformulates position parametrization, velocity decomposition, perception range, label assignment and loss function in polar coordinate system. Polar Parametrization establishes explicit associations between image patterns and prediction targets, exploiting the view symmetry of surround-view cameras as inductive bias to ease optimization and boost performance. Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR. PolarDETR achieves promising performance-speed trade-off on different backbone configurations. Besides, PolarDETR ranks 1st on the leaderboard of nuScenes benchmark in terms of both 3D detection and 3D tracking at the submission time (Mar. 4th, 2022). Code will be released at \url{https://github.com/hustvl/PolarDETR}.
title Polar Parametrization for Vision-based Surround-View 3D Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2206.10965