PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
- URL: http://arxiv.org/abs/2308.03982v2
- Date: Sat, 2 Dec 2023 08:00:53 GMT
- Title: PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
- Authors: Ming Nie, Yujing Xue, Chunwei Wang, Chaoqiang Ye, Hang Xu, Xinge Zhu,
Qingqiu Huang, Michael Bi Mi, Xinchao Wang, Li Zhang
- Abstract summary: We present PARTNER, a novel 3D object detector in the polar coordinate.
Our method outperforms the previous polar-based works with remarkable margins of 3.68% and 9.15% on and ONCE validation set.
- Score: 81.16859686137435
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, polar-based representation has shown promising properties in
perceptual tasks. In addition to Cartesian-based approaches, which separate
point clouds unevenly, representing point clouds as polar grids has been
recognized as an alternative due to (1) its advantage in robust performance
under different resolutions and (2) its superiority in streaming-based
approaches. However, state-of-the-art polar-based detection methods inevitably
suffer from the feature distortion problem because of the non-uniform division
of polar representation, resulting in a non-negligible performance gap compared
to Cartesian-based approaches. To tackle this issue, we present PARTNER, a
novel 3D object detector in the polar coordinate. PARTNER alleviates the
dilemma of feature distortion with global representation re-alignment and
facilitates the regression by introducing instance-level geometric information
into the detection head. Extensive experiments show overwhelming advantages in
streaming-based detection and different resolutions. Furthermore, our method
outperforms the previous polar-based works with remarkable margins of 3.68% and
9.15% on Waymo and ONCE validation set, thus achieving competitive results over
the state-of-the-art methods.
Related papers
- Video Frame Interpolation for Polarization via Swin-Transformer [9.10220649654041]
Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored.
This study proposes a multi-stage and multi-scale network called Swin-VFI based on the Swin-Transformer.
Experimental results demonstrate our approach's superior reconstruction accuracy across all tasks.
arXiv Detail & Related papers (2024-06-17T09:48:54Z) - Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection [108.672972439282]
We introduce a novel decoupled pseudo-labeling (DPL) approach for SSM3OD.
Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels.
We also present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels.
arXiv Detail & Related papers (2024-03-26T05:12:18Z) - Detecting Rotated Objects as Gaussian Distributions and Its 3-D
Generalization [81.29406957201458]
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects.
We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection.
We propose to model the rotated objects as Gaussian distributions.
We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
arXiv Detail & Related papers (2022-09-22T07:50:48Z) - PolarFormer: Multi-camera 3D Object Detection with Polar Transformers [93.49713023975727]
3D object detection in autonomous driving aims to reason "what" and "where" the objects of interest present in a 3D world.
Existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis.
We propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird's-eye-view (BEV) taking as input only multi-camera 2D images.
arXiv Detail & Related papers (2022-06-30T16:32:48Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - Investigating Spherical Epipolar Rectification for Multi-View Stereo 3D
Reconstruction [1.0152838128195467]
We propose a spherical model for epipolar rectification to minimize distortions caused by differences in principal rays.
We show through qualitative and quantitative evaluation that the proposed approach performs better than frame-based epipolar correction.
arXiv Detail & Related papers (2022-04-08T15:50:20Z) - The KFIoU Loss for Rotated Object Detection [115.334070064346]
In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss.
Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU.
The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
arXiv Detail & Related papers (2022-01-29T10:54:57Z) - A recursive robust filtering approach for 3D registration [3.5270468102327004]
The proposed method has four advantages that have not yet occurred altogether in any previous solution.
It is able to deal with inherent noise contaminating sensory data.
It is robust to uncertainties caused by noisy feature localisation.
arXiv Detail & Related papers (2021-10-28T07:50:02Z) - Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D
Object Detection? [44.74595167179931]
We show experimentally that validation results published by PL-based methods are substantially biased.
We introduce a novel deep architecture which introduces a 3D confidence prediction module.
We show that 3D confidence estimation techniques derived from RGB-only 3D detection approaches can be successfully integrated into our framework.
arXiv Detail & Related papers (2020-12-10T16:31:41Z) - Objects detection for remote sensing images based on polar coordinates [26.640452563317346]
We introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet)
In P-RSDet method, arbitrary-oriented object detection can be achieved by predicting the center point and regressing one polar radius and two polar angles.
Experiments on DOTA, UCAS-AOD and NWPU VHR-10 datasets show that our P-RSDet achieves state-of-the-art performances with simpler model and less regression parameters.
arXiv Detail & Related papers (2020-01-09T14:02:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.