Center Focusing Network for Real-Time LiDAR Panoptic Segmentation
- URL: http://arxiv.org/abs/2311.09499v1
- Date: Thu, 16 Nov 2023 01:52:11 GMT
- Title: Center Focusing Network for Real-Time LiDAR Panoptic Segmentation
- Authors: Xiaoyan Li, Gang Zhang, Boyue Wang, Yongli Hu, Baocai Yin
- Abstract summary: A novel center focusing network (CFNet) is introduced to achieve accurate and real-time LiDAR panoptic segmentation.
CFFE is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers.
Our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method.
- Score: 58.1194137706868
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: LiDAR panoptic segmentation facilitates an autonomous vehicle to
comprehensively understand the surrounding objects and scenes and is required
to run in real time. The recent proposal-free methods accelerate the algorithm,
but their effectiveness and efficiency are still limited owing to the
difficulty of modeling non-existent instance centers and the costly
center-based clustering modules. To achieve accurate and real-time LiDAR
panoptic segmentation, a novel center focusing network (CFNet) is introduced.
Specifically, the center focusing feature encoding (CFFE) is proposed to
explicitly understand the relationships between the original LiDAR points and
virtual instance centers by shifting the LiDAR points and filling in the center
points. Moreover, to leverage the redundantly detected centers, a fast center
deduplication module (CDM) is proposed to select only one center for each
instance. Experiments on the SemanticKITTI and nuScenes panoptic segmentation
benchmarks demonstrate that our CFNet outperforms all existing methods by a
large margin and is 1.6 times faster than the most efficient method. The code
is available at https://github.com/GangZhang842/CFNet.
Related papers
- Fuzzy K-Means Clustering without Cluster Centroids [79.19713746387337]
Fuzzy K-Means clustering is a critical computation technique in unsupervised data analysis.
This paper proposes a novel Fuzzy K-Means clustering algorithm that entirely eliminates the reliance on cluster centroids.
arXiv Detail & Related papers (2024-04-07T12:25:03Z) - Lidar Panoptic Segmentation and Tracking without Bells and Whistles [48.078270195629415]
We propose a detection-centric network for lidar segmentation and tracking.
One of the core components of our network is the object instance detection branch.
We evaluate our method on several 3D/4D LPS benchmarks and observe that our model establishes a new state-of-the-art among open-sourced models.
arXiv Detail & Related papers (2023-10-19T04:44:43Z) - Feature Selection using Sparse Adaptive Bottleneck Centroid-Encoder [1.2487990897680423]
We introduce a novel nonlinear model, Sparse Adaptive Bottleneckid-Encoder (SABCE), for determining the features that discriminate between two or more classes.
The algorithm is applied to various real-world data sets, including high-dimensional biological, image, speech, and accelerometer sensor data.
arXiv Detail & Related papers (2023-06-07T21:37:21Z) - Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic
Segmentation via Clustering Pseudo Heatmap [9.770808277353128]
We propose a fast and high-performance LiDAR-based framework, referred to as Panoptic-PHNet.
We introduce a clustering pseudo heatmap as a new paradigm, which, followed by a center grouping module, yields instance centers for efficient clustering.
For backbone design, we fuse the fine-grained voxel features and the 2D Bird's Eye View (BEV) features with different receptive fields to utilize both detailed and global information.
arXiv Detail & Related papers (2022-05-14T08:16:13Z) - CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds [2.891413712995641]
We propose a novel real-time end-to-end panoptic segmentation network for LiDAR point clouds, called CPSeg.
CPSeg comprises a shared encoder, a dual decoder, a task-aware attention module (TAM) and a cluster-free instance segmentation head.
arXiv Detail & Related papers (2021-11-02T16:44:06Z) - SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional
Attention Clustering [1.1470070927586016]
We present a learnable sparse multi-directional attention clustering to segment multi-scale foreground instances.
SMAC-Seg is a real-time clustering-based approach, which removes the complex proposal network to segment instances.
Our experimental results show that SMAC-Seg achieves state-of-the-art performance among all real-time deployable networks.
arXiv Detail & Related papers (2021-08-31T02:25:01Z) - F2Net: Learning to Focus on the Foreground for Unsupervised Video Object
Segmentation [61.74261802856947]
We propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects.
Our proposed network consists of three main parts: Siamese Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion Module.
Experiments on DAVIS2016, Youtube-object, and FBMS datasets show that our proposed F2Net achieves the state-of-the-art performance with significant improvement.
arXiv Detail & Related papers (2020-12-04T11:30:50Z) - (k, l)-Medians Clustering of Trajectories Using Continuous Dynamic Time
Warping [57.316437798033974]
In this work we consider the problem of center-based clustering of trajectories.
We propose the usage of a continuous version of DTW as distance measure, which we call continuous dynamic time warping (CDTW)
We show a practical way to compute a center from a set of trajectories and subsequently iteratively improve it.
arXiv Detail & Related papers (2020-12-01T13:17:27Z) - LiDAR-based Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
LiDAR-based panoptic segmentation aims to parse both objects and scenes in a unified manner.
We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm.
Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods.
arXiv Detail & Related papers (2020-11-24T08:44:46Z) - Learning Gaussian Instance Segmentation in Point Clouds [26.711177503253946]
This paper presents a novel method for instance segmentation of 3D point clouds.
The proposed method is called Gaussian Instance Center Network (GICN), which can approximate the distributions of instance centers scattered in the whole scene as Gaussian center heatmaps.
Our method achieves state-of-the-art performance in the task of 3D instance segmentation on ScanNet and S3DIS datasets.
arXiv Detail & Related papers (2020-07-20T03:11:32Z)
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.